Intelligent management and control method and system for steelmaking steam system

Abstract

The invention discloses an intelligent management and control method and system for a steelmaking steam system, and the method comprises the steps: collecting the multi-source data of the steelmaking steam system through a data collection layer, and enabling the multi-source data to comprise pipe network pressure data, steam flow data, converter production plan data, RH furnace production plan data and heat accumulator pressure data; a multi-element intelligent model is constructed on an intelligent analysis layer, according to the multi-source data, the steam production, consumption and storage trend in a future preset time period is predicted through the multi-element intelligent model, and a PLC control strategy is generated in combination with a preset pipe network pressure safety boundary; and dynamic closed-loop control is carried out on a heat accumulator valve in an application control layer according to a PLC control strategy, so that the pressure fluctuation of the heat accumulator is within a target range. In this way, the steam utilization efficiency can be improved in an assisted mode, production stability is guaranteed, and energy cost is reduced.

Description

Technical Field

[0001] This invention relates to the field of steelmaking technology, and in particular to an intelligent control method and system for steelmaking steam systems. Background Technology

[0002] In steelmaking, steam, as a critical secondary energy source, directly impacts production and costs due to its supply stability and utilization efficiency. However, traditional steam system monitoring and management suffer from numerous problems. Regarding data transmission and processing, reliance on wired networks leads to complex cabling that struggles to cover dispersed equipment. Data from different subsystems becomes isolated, hindering global energy efficiency analysis. Command transmission latency reaches 200-500ms, and single-point data acquisition cannot coordinate with multi-source data. In terms of control and management, manual parameter inspection and valve adjustment are inefficient and inaccurate. Alarms rely solely on fixed thresholds, lacking intelligent analysis capabilities and the ability to predict supply and demand and equipment degradation trends. The system architecture is limited, lacking a layered design, with weak data processing capabilities, poor wired network scalability, difficulty in integrating new equipment, and the absence of an SQL database to support historical data tracing. This results in limited energy efficiency optimization, delayed fault response, insufficient preventative maintenance, and difficulty in achieving refined energy management and intelligent scheduling. Summary of the Invention

[0003] In view of the above problems, the present invention provides an intelligent control method and system for steelmaking steam systems to optimize the impact of steam on steelmaking production and costs.

[0004] According to a first aspect of the present invention, a method for intelligent control of a steelmaking steam system is provided, comprising: Multi-source data of the steelmaking steam system is collected through the data acquisition layer. The multi-source data includes pipeline pressure data, steam flow data, converter production plan data, RH furnace production plan data, and accumulator pressure data. The multi-source data is transmitted to the hyperconverged server through a three-tier network and stored in an SQL database. A multi-source intelligent model is constructed in the intelligent analysis layer. Based on the multi-source data, the steam production, consumption and storage trends within a preset time period are predicted through the multi-source intelligent model. Combined with the preset pipeline pressure safety boundary, a PLC control strategy is generated. In the application control layer, dynamic closed-loop control of the accumulator valves is performed according to the PLC control strategy to keep the accumulator pressure fluctuation within the target range, which is 2.6MPa-3.2MPa.

[0005] Optionally, the data acquisition layer includes a pressure sensor and a flow meter. The pressure sensor is used to acquire pipeline pressure and accumulator pressure data, and the flow meter is used to acquire steam flow data.

[0006] Optionally, the method further includes: Monitor the operating status of the steelmaking steam system. If extreme or abnormal conditions occur, trigger an audible and visual alarm and push the alarm information to the user terminal.

[0007] Optionally, the criteria for determining the extreme operating conditions include: The instantaneous fluctuation of pipeline pressure is greater than 0.5 MPa / min, the accumulator pressure exceeds the range of 2.6 MPa-3.2 MPa and continues for a first duration, or the change in steam flow rate within a second duration is greater than the preset range.

[0008] Optionally, the pipeline pressure safety boundary is taken from the range of 3.0MPa-4.0MPa.

[0009] Optional: The operating status parameters of the converter, RH furnace, deaerator, and accumulator are displayed on the visual monitoring interface.

[0010] Optional, also includes: Based on the steam flow rate data, determine the steam production data and steam consumption data; Based on the steam production data and steam consumption data, and combined with the carbon emission coefficients of each process, the carbon emissions from steam consumption in the converter blowing, RH furnace refining, and deaerator operation processes are quantified to generate carbon footprint information.

[0011] Optional: The multi-dimensional intelligent model includes a converter steam production prediction model, an RH furnace steam consumption prediction model, a deaerator steam consumption prediction model, a steelmaking steam scheduling model based on production plans, and a steelmaking steam adaptive dynamic optimization model.

[0012] According to a second aspect of the present invention, an intelligent control system for a steelmaking steam system is provided, comprising: The data acquisition layer collects multi-source data from the steelmaking steam system, including pipeline pressure data, steam flow data, converter production plan data, RH furnace production plan data, and accumulator pressure data. The multi-source data is then transmitted to the hyperconverged server via a three-level network and stored in an SQL database. The intelligent analysis layer constructs a multi-source intelligent model. Based on the multi-source data, the multi-source intelligent model predicts the steam production, consumption and storage trends within a preset time period and generates a PLC control strategy by combining the preset pipeline pressure safety boundary. In the application control layer, the accumulator valves are dynamically closed-loop controlled according to the PLC control strategy to keep the accumulator pressure fluctuation within the target range, which is 2.6MPa-3.2MPa.

[0013] According to a third aspect of the present invention, a steelmaking equipment is provided, including the aforementioned intelligent control system for a steelmaking steam system.

[0014] The above-described one or more technical solutions in the embodiments of this specification have at least the following technical effects: This specification provides an intelligent management and control method and system for a steelmaking steam system. The system collects multi-source data from the steelmaking steam system through a data acquisition layer. This multi-source data includes pipeline pressure data, steam flow data, converter production plan data, RH furnace production plan data, and accumulator pressure data. The multi-source data is transmitted to a hyper-converged server via a three-level network and stored in an SQL database. A multivariate intelligent model is constructed at the intelligent analysis layer. Based on the multi-source data, the model predicts the steam production, consumption, and storage trends within a preset time period and, combined with a preset pipeline pressure safety boundary, generates a PLC control strategy. At the application control layer, the accumulator valves are dynamically controlled in a closed-loop manner according to the PLC control strategy, ensuring that accumulator pressure fluctuations remain within a target range. This approach helps improve steam utilization efficiency, ensure stable production, and reduce energy costs.

[0015] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0016] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference figures denote the same parts throughout the drawings. In the drawings: Figure 1 A flowchart of an intelligent control method for a steelmaking steam system is shown in an embodiment of the present invention.

[0017] Figure 2 A block diagram of an intelligent control device for a steelmaking steam system is shown in an embodiment of the present invention. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0019] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0020] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0021] In the description of this invention, it should also be noted that, unless otherwise explicitly specified and limited, the terms "set," "install," "connect," and "link" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0022] This invention provides an intelligent control method for a steelmaking steam system, combined with... Figure 1 The flowchart shown illustrates that the intelligent control method for the steelmaking steam system includes steps 101 to 103: Step 101: Collect multi-source data of the steelmaking steam system through the data acquisition layer. The multi-source data includes pipeline pressure data, steam flow data, converter production plan data, RH furnace production plan data, accumulator pressure data, and ambient temperature. In this embodiment, multi-source data refers to various types of data that can comprehensively reflect the supply and demand and operating status of the steam system. Among them, pipeline pressure data is used to reflect the pressure stability of the steam transmission pipeline network, steam flow data is used to reflect the rate of steam generation and consumption, converter and RH furnace (RH Vacuum Degassing Furnace) production plan data is used to predict the production rhythm and steam demand changes of steam-consuming equipment, and accumulator pressure data is used to reflect the load status of steam storage equipment. These data together constitute the basic data source for intelligent control.

[0023] The data acquisition layer includes pressure sensors and flow meters for data collection. The pressure sensors collect pipeline pressure and accumulator pressure data, while the flow meters collect steam flow data. Other multi-source data can be obtained by the data acquisition layer through other channels.

[0024] The multi-source data is then transmitted to the hyperconverged server via a three-tier network and stored in an SQL database.

[0025] A three-tiered network is a hierarchical network architecture for efficient data transmission. It typically includes a field device layer (communication between sensors and devices), a workshop-level network (data aggregation within the area), and a plant-level network (data transmission from the entire system to the hyperconverged server). This avoids data transmission delays caused by congestion in a single network, ensuring data real-time performance. The hyperconverged server is an integrated device combining computing, storage, and networking functions. It can efficiently handle concurrent read / write requests from multiple data sources, providing computing power support for subsequent intelligent model calculations. Combined with an SQL database, it enables long-term storage and relational queries of production plans, real-time operations, and historical data, solving the problems of data silos and traceability difficulties in traditional systems.

[0026] Compared to traditional wired single-point data acquisition, this embodiment achieves seamless data acquisition and low latency (transmission latency < 50ms) through multi-device collaborative acquisition and 5G / three-level network transmission, ensuring that the data can accurately and promptly reflect the system's operating status.

[0027] Step 102: Construct a multivariate intelligent model in the intelligent analysis layer. Based on the multi-source data, predict the steam production, consumption and storage trends within a preset time period through the multivariate intelligent model, and generate a PLC control strategy by combining the preset pipeline pressure safety boundary; wherein, the pipeline pressure safety boundary is taken from the range of 3.0MPa-4.0MPa.

[0028] In this embodiment, the multi-dimensional intelligence model refers to the core tool that uses algorithms to mine data correlation patterns and predict steam production, consumption, and inventory trends. Its specific structure and operational logic will be explained in detail in subsequent embodiments. The preset duration is typically set to 2 hours (the specific duration can be determined based on the steelmaking production rhythm and the steam system response speed), allowing for advance prediction of supply and demand changes.

[0029] In an optional embodiment, the multi-dimensional intelligent model includes a converter steam production prediction model, an RH furnace steam consumption prediction model, a deaerator steam consumption prediction model, a steelmaking steam scheduling model based on production plans, and a steelmaking steam adaptive dynamic optimization model.

[0030] It is easy to see that the multiple intelligences model consists of five collaborative models. Each model independently completes a specific prediction task, while also being interconnected to form an overall decision, as follows: The inputs to the converter steam production prediction model are converter production plan data (such as blowing time and molten steel tonnage), converter flue gas temperature data (collected through an additional temperature sensor), and historical converter steam production data (retrieved from an SQL database). The model output is the predicted hourly steam production of the converter over the next two hours. For example, predicting a production of 60 t / h for the first hour and 55 t / h for the second hour provides a basis for assessing steam supply capacity.

[0031] The inputs to the RH furnace steam consumption prediction model are RH furnace production plan data (such as refined steel grades and refining time), historical RH furnace steam consumption data, and current molten steel temperature data (retrieved from the RH furnace control system). The model outputs the predicted hourly steam consumption of the RH furnace over the next two hours. For example, predicting a consumption of 30 t / h in the first hour and 25 t / h in the second hour, anticipating changes in demand for major steam-consuming equipment.

[0032] The inputs to the deaerator steam consumption prediction model are deaerator inlet water flow rate data (collected via an inlet water flow meter), inlet water temperature data, and historical deaerator steam consumption data. The model output is the predicted hourly steam consumption of the deaerator over the next two hours. For example, a predicted hourly consumption of 10 t / h can supplement the demand forecast for secondary steam-using equipment.

[0033] The inputs to the steelmaking steam scheduling model based on production planning are the prediction results of the first three sub-models (production output, RH furnace consumption, and deaerator consumption), the current pressure data of the accumulator, and the pipeline pressure safety boundary. The output of the model is the steam scheduling scheme (e.g., when the predicted production output is greater than the total consumption, it is recommended to increase the steam intake of the accumulator; when the production output is less than the consumption, it is recommended to release the steam stored in the accumulator), providing a basis for subsequent model optimization decisions.

[0034] The inputs to the steelmaking steam adaptive dynamic optimization model are the scheduling model scheme, real-time steam flow data, accumulator pressure data, and historical optimization cases (retrieved from an SQL database). The model output is the final PLC control strategy (e.g., accumulator inlet valve opening 50%, RH boiler steam valve opening 80%), ensuring that the strategy can both meet supply and demand balance and maintain accumulator pressure within the range of 2.6MPa-3.2MPa.

[0035] Each sub-model is built based on machine learning algorithms (such as gradient boosting trees and neural networks), and its prediction accuracy and policy adaptability are improved through regular iterative optimization (such as updating model parameters monthly with newly collected data). This embodiment clarifies the composition and operation logic of the multiple intelligence model, transforming the intelligent analysis layer in the embodiment into a practical technical module, while providing core computing power support for the entire intelligent management and control method.

[0036] Step 103: In the application control layer, the accumulator valves are dynamically closed-loop controlled according to the PLC control strategy to keep the accumulator pressure fluctuation within the target range, which is 2.6MPa-3.2MPa.

[0037] In this embodiment, the pipeline pressure safety boundary refers to the upper limit threshold of pressure set to ensure the safe operation of the steam system, ranging from 3.0MPa to 4.0MPa (e.g., 3.5MPa under normal operating conditions), to avoid excessive pressure leading to pipeline leakage or equipment damage; the PLC control strategy is to convert the decisions of the intelligent model into executable instructions (e.g., valve opening adjustment parameters).

[0038] The dynamic closed-loop control of the accumulator valves automatically adjusts the valve opening by collecting accumulator pressure data in real time and comparing it with the target fluctuation range (2.6MPa-3.2MPa). For example, the vent valve is opened wider when the pressure is higher than 3.2MPa, and the steam inlet valve is opened wider when the pressure is lower than 2.6MPa. This maintains stable pressure without manual intervention and solves the problems of low accuracy and slow response of traditional manual adjustment.

[0039] In addition, this embodiment adds a system operation status monitoring and alarm mechanism to solve the problem of delayed fault detection in traditional systems, further improving the safety and reliability of the steam system. Specifically, this includes: Monitor the operating status of the steelmaking steam system. If extreme or abnormal conditions occur, trigger an audible and visual alarm and push the alarm information to the user terminal.

[0040] Among them, the operation status monitoring is achieved by collecting the output data of pressure sensors and flow meters in real time, combined with the production status of converter / RH furnace (such as whether it is in the blowing or refining stage), to comprehensively monitor the supply and demand balance of steam system, equipment operation status (such as whether valves are stuck) and pipeline pressure stability. The monitoring frequency is synchronized with the data acquisition frequency (usually once per second).

[0041] Extreme operating conditions or abnormal states refer to situations that exceed the normal operating range of the system, such as sudden rises or falls in pipeline pressure, continuous deviations of accumulator pressure from the target range, and abnormal fluctuations in steam flow. If these situations are not handled promptly, they may lead to production interruptions or equipment damage. The specific criteria for determining extreme operating conditions are as follows: The instantaneous pressure fluctuation in the pipeline network is greater than 0.5 MPa / min; instantaneous fluctuation refers to the ratio of the pressure difference between two consecutive sampling cycles to the time interval. For example, if the pressure rises from 3.0 MPa to 3.5 MPa within 1 second, the fluctuation rate is 0.5 MPa / s (far exceeding 0.5 MPa / min). This is considered an extreme operating condition, which may be caused by a sudden increase in steam production or a sudden decrease in steam consumption.

[0042] If the pressure of the accumulator exceeds the range of 2.6MPa-3.2MPa and remains there for a first duration, the first duration is usually set to 10 seconds (determined based on the accumulator volume and the steam system response speed). If the pressure briefly exceeds the range (e.g., recovers within 2 seconds), it may be a momentary disturbance and no alarm is required. If it continues for more than 10 seconds, it indicates that the valve regulation has failed or there is a serious imbalance between supply and demand, and an alarm needs to be triggered.

[0043] Or the steam flow rate changes by more than a preset range (e.g., 30%) within a second time period. The second time period can be set to 1 minute, and the range of change refers to the absolute value of (current flow rate - flow rate 1 minute ago) / flow rate 1 minute ago. For example, if the flow rate drops suddenly from 50t / h to 30t / h, the range of change is 40%, which may be caused by a sudden shutdown of the steam-using equipment or a malfunction of the waste heat recovery system, and should be investigated in a timely manner.

[0044] In addition, this embodiment also provides an intuitive display of the system's operating status through a visual monitoring interface, such as displaying the operating status parameters of the converter, RH furnace, deaerator, and regenerator. This allows managers to remotely grasp the overall situation and provides data support for adjusting safety boundaries and troubleshooting.

[0045] In an optional embodiment, it further includes: Based on the steam flow rate data, determine the steam production data and steam consumption data; Based on the steam production data and steam consumption data, and combined with the carbon emission coefficients of each process, the carbon emissions from steam consumption in the converter blowing, RH furnace refining, and deaerator operation processes are quantified to generate carbon footprint information.

[0046] This embodiment calculates production and consumption using steam flow data and quantifies carbon emissions for each process by combining carbon emission coefficients, thus meeting the requirements of low-carbon management.

[0047] Among them, steam production data and steam consumption data can be calculated based on the flow data collected by the flow meter: Steam production = cumulative value of the converter waste heat recovery outlet flow meter (unit: t); Steam consumption = cumulative value of the RH boiler steam inlet flow meter + cumulative value of the deaerator steam inlet flow meter (unit: t). The calculation cycle is usually 1 hour to ensure that the data matches the production shift.

[0048] The process carbon emission factor refers to the carbon emission amount corresponding to 1 ton of steam consumed (unit: kgCO2 / t).

[0049] The carbon footprint information includes the steam consumption of each process, the corresponding carbon emissions, and the total carbon emissions (e.g., the converter blowing process consumes 50t of steam and emits 4000kgCO2; the RH furnace refining process consumes 30t of steam and emits 2400kgCO2). It is displayed in the form of reports or curves and supports monthly / quarterly traceability, providing a basis for enterprises to formulate emission reduction measures.

[0050] In summary, the intelligent management and control method for a steelmaking steam system provided in this specification involves collecting multi-source data from the steelmaking steam system through a data acquisition layer. This multi-source data includes pipeline pressure data, steam flow data, converter production plan data, RH furnace production plan data, and accumulator pressure data. The multi-source data is transmitted to a hyper-converged server via a three-level network and stored in an SQL database. A multivariate intelligent model is constructed at the intelligent analysis layer. Based on the multi-source data, the model predicts the steam production, consumption, and storage trends over a preset time period and, combined with a preset pipeline pressure safety boundary, generates a PLC control strategy. At the application control layer, the accumulator valves are dynamically controlled in a closed-loop manner according to the PLC control strategy, ensuring that accumulator pressure fluctuations remain within a target range. This approach can help improve steam utilization efficiency, ensure stable production, and reduce energy costs.

[0051] Based on the same inventive concept, combined with Figure 2 As shown in the figure, this embodiment of the invention also provides an intelligent control system for a steelmaking steam system, comprising: The data acquisition layer collects multi-source data from the steelmaking steam system, including pipeline pressure data, steam flow data, converter production plan data, RH furnace production plan data, and accumulator pressure data. The multi-source data is then transmitted to the hyperconverged server via a three-level network and stored in an SQL database. The intelligent analysis layer constructs a multi-source intelligent model. Based on the multi-source data, the multi-source intelligent model predicts the steam production, consumption and storage trends within a preset time period and generates a PLC control strategy by combining the preset pipeline pressure safety boundary. In the application control layer, the accumulator valves are dynamically closed-loop controlled according to the PLC control strategy to keep the accumulator pressure fluctuation within the target range, which is 2.6MPa-3.2MPa.

[0052] Optionally, the data acquisition layer includes a pressure sensor and a flow meter. The pressure sensor is used to acquire pipeline pressure and accumulator pressure data, and the flow meter is used to acquire steam flow data.

[0053] Optionally, the application control layer is also used for: Monitor the operating status of the steelmaking steam system. If extreme or abnormal conditions occur, trigger an audible and visual alarm and push the alarm information to the user terminal.

[0054] Optionally, the application control layer is also used for: The instantaneous fluctuation of pipeline pressure is greater than 0.5 MPa / min, the accumulator pressure exceeds the range of 2.6 MPa-3.2 MPa and continues for a first duration, or the change in steam flow rate within a second duration is greater than the preset range.

[0055] Optionally, the pipeline pressure safety boundary is taken from the range of 3.0MPa-4.0MPa.

[0056] Optionally, the application control layer is also used for: The operating status parameters of the converter, RH furnace, deaerator, and accumulator are displayed on the visual monitoring interface.

[0057] Optionally, the application control layer is also used for: Based on the steam flow rate data, determine the steam production data and steam consumption data; Based on the steam production data and steam consumption data, and combined with the carbon emission coefficients of each process, the carbon emissions from steam consumption in the converter blowing, RH furnace refining, and deaerator operation processes are quantified to generate carbon footprint information.

[0058] Optionally, the multi-dimensional intelligent model includes a converter steam production prediction model, an RH furnace steam consumption prediction model, a deaerator steam consumption prediction model, a steelmaking steam scheduling model based on production plans, and a steelmaking steam adaptive dynamic optimization model.

[0059] In summary, the intelligent management and control method and system for a steelmaking steam system provided in this specification collects multi-source data from the steelmaking steam system through a data acquisition layer. This multi-source data includes pipeline pressure data, steam flow data, converter production plan data, RH furnace production plan data, and accumulator pressure data. The multi-source data is transmitted to a hyper-converged server via a three-level network and stored in an SQL database. A multivariate intelligent model is constructed at the intelligent analysis layer. Based on the multi-source data, the model predicts the steam production, consumption, and storage trends within a preset time period and, combined with a preset pipeline pressure safety boundary, generates a PLC control strategy. At the application control layer, the accumulator valves are dynamically controlled in a closed-loop manner according to the PLC control strategy, ensuring that accumulator pressure fluctuations remain within the target range. This approach helps improve steam utilization efficiency, ensure stable production, and reduce energy costs.

[0060] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the intelligent control system for steelmaking steam systems described above can be referred to the corresponding process in the aforementioned method, and will not be elaborated further here.

[0061] Based on the same inventive concept, embodiments of the present invention also provide a steelmaking equipment, including the aforementioned intelligent control system for steelmaking steam systems.

[0062] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the vehicle controller described above can be referred to the corresponding process in the aforementioned method, and will not be elaborated further here.

[0063] The above are merely various embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. An intelligent management and control method for a steelmaking steam system, characterized in that, include: Multi-source data of the steelmaking steam system is collected through the data acquisition layer. The multi-source data includes pipeline pressure data, steam flow data, converter production plan data, RH furnace production plan data, and accumulator pressure data. A multi-source intelligent model is constructed in the intelligent analysis layer. Based on the multi-source data, the steam production, consumption and storage trends within a preset time period are predicted through the multi-source intelligent model. Combined with the preset pipeline pressure safety boundary, a PLC control strategy is generated. In the application control layer, dynamic closed-loop control of the accumulator valves is performed according to the PLC control strategy to keep the accumulator pressure fluctuation within the target range.

2. The intelligent control method for steelmaking steam systems according to claim 1, characterized in that, The target range is 2.6MPa-3.2MPa.

3. The intelligent control method for steelmaking steam systems according to claim 1, characterized in that, The method further includes: Monitor the operating status of the steelmaking steam system. If extreme or abnormal conditions occur, trigger an audible and visual alarm and push the alarm information to the user terminal.

4. The intelligent control method for steelmaking steam systems according to claim 3, characterized in that, The criteria for determining the extreme operating conditions include: The instantaneous fluctuation of pipeline pressure is greater than 0.5 MPa / min, the accumulator pressure exceeds the range of 2.6 MPa-3.2 MPa and continues for a first duration, or the change in steam flow rate within a second duration is greater than the preset range.

5. The intelligent control method for steelmaking steam systems according to claim 1, characterized in that, The pipeline pressure safety boundary is taken from the range of 3.0MPa-4.0MPa.

6. The intelligent control method for steelmaking steam system according to claim 1, characterized in that, Also includes: Based on the steam flow rate data, determine the steam production data and steam consumption data; Based on the steam production data and steam consumption data, and combined with the carbon emission coefficients of each process, the carbon emissions from steam consumption in the converter blowing, RH furnace refining, and deaerator operation processes are quantified to generate carbon footprint information.

7. The intelligent control method for steelmaking steam systems according to claim 1, characterized in that, The multi-dimensional intelligent model includes a converter steam production prediction model, an RH furnace steam consumption prediction model, a deaerator steam consumption prediction model, a steelmaking steam scheduling model based on production plans, and a steelmaking steam adaptive dynamic optimization model.

8. The intelligent control method for steelmaking steam systems according to claim 1, characterized in that, The method further includes: The operating status parameters of the converter, RH furnace, deaerator, and accumulator are displayed on the visual monitoring interface.

9. An intelligent control system for a steelmaking steam system, characterized in that, include: The data acquisition layer collects multi-source data from the steelmaking steam system, including pipeline pressure data, steam flow data, converter production plan data, RH furnace production plan data, and accumulator pressure data. The intelligent analysis layer constructs a multi-source intelligent model. Based on the multi-source data, the multi-source intelligent model predicts the steam production, consumption and storage trends within a preset time period and generates a PLC control strategy by combining the preset pipeline pressure safety boundary. In the application control layer, dynamic closed-loop control of the accumulator valves is performed according to the PLC control strategy to keep the accumulator pressure fluctuation within the target range.

10. A steelmaking equipment, characterized in that, Including the intelligent control system for steelmaking steam system as described in claim 9.

Images