Steel mill air substation area oxygen supply and demand balance control system
Through the integrated control system of data acquisition, intelligent prediction, dynamic scheduling and human-computer interaction modules, the problem of insufficient traditional oxygen demand prediction models is solved, and the dynamic balance of oxygen supply and demand and the improvement of production efficiency is achieved.
Patent Information
- Application Number
- CN202411688955.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-25
- Publication Date
- 2025-03-18
AI Technical Summary
In actual application, the traditional oxygen demand forecasting model has simple algorithms and structures, and is difficult to adapt to new data and future demand, which makes it difficult to achieve a balance between oxygen supply and demand.
Design a oxygen supply and demand balance control system for the steel plant air sub-station area integrating data acquisition module, intelligent prediction module, dynamic scheduling module and human-computer interaction module. Through real-time monitoring, accurate prediction and dynamic scheduling, the balance of oxygen supply and demand is achieved.
It improves the accuracy and reliability of oxygen demand forecasts, achieves a dynamic balance between oxygen supply and demand, improves production efficiency and resource utilization, and reduces production costs.
Smart Images
Figure CN119648131A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of industrial automation and control systems, and in particular to an oxygen supply and demand balance control system for an air separation station in a steel plant. Background Art
[0002] In the steel production process, oxygen is an important industrial gas, and its supply stability and balance have a significant impact on steelmaking efficiency, product quality and production costs. The steel plant air separation station is a key link in oxygen production, storage and supply. Its operating efficiency and management level are directly related to the smooth operation of the entire steel production line.
[0003] Although there are some intelligent prediction modules in traditional technologies for predicting oxygen demand, these modules still have many shortcomings in practical applications. The algorithms and structures of traditional prediction models are relatively simple, and it is difficult to apply the optimized models to new data to predict oxygen demand in the future. Therefore, it is particularly important to develop an oxygen supply and demand balance control system for the air separation station area of a steel plant. Summary of the invention
[0004] The purpose of the present invention is to make up for the deficiencies of the prior art and to provide an oxygen supply and demand balance control system and system for an air separation station in a steel plant. The system realizes real-time monitoring, accurate prediction and dynamic scheduling of oxygen supply and demand by integrating a data acquisition module, an intelligent prediction module, a dynamic scheduling module and a human-computer interaction module, thereby providing strong technical support for production optimization and cost control of steel enterprises.
[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: an electronic balance data acquisition and analysis system, the system comprising a data acquisition module, an intelligent prediction module, a dynamic scheduling module and a human-computer interaction module;
[0006] The data acquisition module is equipped with high-precision sensors to monitor the oxygen flow, pressure, and temperature parameters of air separation equipment, oxygen storage tanks, and steelmaking equipment in real time, collect steelmaking production plans, equipment operation records, and historical oxygen supply and demand data, and provide data support for intelligent prediction;
[0007] The intelligent prediction module: comprehensively collects historical oxygen supply and demand data from the data center, which covers real-time monitoring information of oxygen flow, pressure, and temperature, as well as steelmaking production plan and equipment operation log related data, cleans and integrates the collected data, and pre-processes the integrated data to lay a solid foundation for subsequent data analysis, so as to better adapt to the input requirements of the prediction model according to the characteristics of the data;
[0008] In-depth analysis of historical data to identify key factors affecting oxygen demand, Among them, S ot represents the oxygen supply and demand state value at time t, g(X) represents a function with input data X as the independent variable, F i (t) is the function of the i-th influencing factor with respect to time t, D i (x) is the data characteristic value of the i-th influencing factor, x represents the relevant data point, w i is the weight coefficient of the i-th influencing factor, E(t) is the error correction term, which is a function of time t. Based on these factors, valuable features are extracted from the data as input variables of the prediction model. According to the characteristics of the data and the prediction requirements, the algorithm is selected to build the oxygen demand prediction model. The model is trained using the preprocessed data and the extracted features. The prediction ability of the model is improved by adjusting the model parameters and algorithm structure.
[0009] Use cross-validation, hold-out method or online learning method to verify the trained model and evaluate its prediction performance. According to the verification results, make necessary adjustments and optimizations to the model to improve the accuracy and generalization ability of the model. Apply the optimized model to new data to predict the oxygen demand in the future. The prediction results should include the predicted value and its confidence interval to reflect the uncertainty of the prediction.
[0010] Conduct in-depth analysis of the forecast results, understand the supply and demand changes and trends behind them, apply the forecast results to actual production scheduling and decision-making, guide the operation adjustment of air separation equipment and oxygen storage systems, and achieve a dynamic balance between oxygen supply and demand. As time goes by and new data is generated, regularly update and maintain the forecast model, introduce new features and data sources, and optimize the model structure and parameters to adapt to the ever-changing production environment and needs;
[0011] The dynamic scheduling module: according to the output results of the intelligent prediction module, automatically adjusts the operating parameters of the oxygen production equipment to match the predicted oxygen demand, monitors the reserves of the oxygen storage tanks in real time, optimizes the oxygen release and replenishment strategies, avoids oxygen waste and shortage, integrates the overall resources of the air separation station area, realizes the coordinated operation of the equipment, and improves the reliability and efficiency of the oxygen supply;
[0012] The human-computer interaction module provides a user-friendly interface, displays real-time oxygen supply and demand data, forecast results and dispatch instruction information, supports manual intervention and adjustment, and allows operators to modify and optimize system forecast and dispatch results according to actual conditions.
[0013] Furthermore, the data acquisition module installs and calibrates high-precision sensors on air separation equipment, oxygen storage tanks and steelmaking equipment in the oxygen supply and demand balance control system of the air separation station area of the steel plant to monitor the oxygen flow, pressure and temperature parameters in real time. Then, the data acquisition equipment is configured to receive sensor signals, and communication parameters are set to ensure communication with the data center. After the data acquisition equipment is started, data is collected according to the set period and frequency, and stored locally and uploaded to the data center. Before uploading the data, format conversion is required to ensure compatibility, and encryption verification is performed during the transmission process to ensure security. After uploading, the data is checked and verified to ensure integrity and accuracy. The data is stored and managed in the data warehouse and applied to intelligent prediction, production monitoring optimization and fault warning diagnosis.
[0014] Furthermore, the intelligent prediction module selects an algorithm to construct an oxygen demand prediction model: Among them, O pred (t) represents the predicted oxygen demand at time t, h represents a mapping function, θ j is the parameter vector related to the jth algorithm, A j (X,t is the jth algorithm basis function based on data X and time t, ∈(t) is the error term.
[0015] Furthermore, the optimized model is applied to new data to predict oxygen demand in the future: Among them, O future (t) represents the predicted oxygen demand at future time t, The M in it represents a mapping function, which transforms the optimized parameter vector New data X new and the future time point t as input, f(t) is the time adjustment function, is the kth parameter obtained after model optimization, B k (X new ) is based on the new data X new The kth characteristic function, g k (t) is the time-dependent uncertainty measure function, and Z is a random variable that obeys the standard normal distribution.
[0016] Furthermore, the dynamic scheduling module receives the future oxygen demand forecast data provided by the intelligent prediction module, and analyzes it to clarify the demand trend. Based on these data, the module automatically adjusts the operating parameters of the oxygen production equipment to ensure that the oxygen production matches the predicted demand. By real-time monitoring of the reserves of oxygen storage tanks and comparing them with the safety inventory standards, the module can optimize the oxygen release and replenishment strategy to avoid waste and shortages.
[0017] Furthermore, the dynamic scheduling module integrates the overall resources of the air separation station area, uniformly manages and schedules all equipment, and automatically adjusts the equipment operation mode and sequence according to real-time demand and equipment status to achieve coordinated operation between equipment and improve resource utilization efficiency. This process may involve load balancing and fault switching strategies, aiming to ensure the timeliness and accuracy of oxygen supply and meet the actual needs of users.
[0018] Furthermore, the human-computer interaction module is designed with an intuitive and easy-to-use user interface to display real-time oxygen supply and demand data, forecast results and future scheduling instructions. The interface is dynamically updated to ensure that operators can grasp the system status at any time and clearly understand the system's future needs and scheduling plans.
[0019] Furthermore, the human-computer interaction module provides an operation interface and supports manual intervention, allowing operators to correct and optimize system prediction and scheduling results according to actual conditions. After the correction is completed, the modified content is confirmed through the interface. The human-computer interaction module passes the update to related modules, and the module collects operator feedback for continuous optimization and improvement of the system.
[0020] Compared with the prior art, an intelligent design method, system and detection method for architectural decoration based on user portraits have the following beneficial effects:
[0021] 1. The present invention identifies the key factors affecting oxygen demand by deeply analyzing historical data, and uses algorithms to build a prediction model to make the prediction results more accurate and reliable. In addition, the present invention also regularly updates and maintains the prediction model, introduces new features and data sources to adapt to the ever-changing production environment and needs. This improvement not only improves the accuracy of the prediction, but also provides more reliable data support for the company's production decisions.
[0022] 2. The present invention realizes real-time monitoring, accurate prediction and dynamic scheduling of oxygen supply and demand in the air separation station area of a steel plant by integrating data acquisition module, intelligent prediction module, dynamic scheduling module and human-computer interaction module. This system provides powerful technical support for the production optimization of steel enterprises, enabling enterprises to grasp the oxygen supply and demand situation more accurately and adjust production plans in time, thereby improving production efficiency and resource utilization. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0024] Figure 1An operation flow chart of an oxygen supply and demand balance control system in an air separation station area of a steel plant. DETAILED DESCRIPTION
[0025] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0026] Embodiment 1
[0027] Install high-precision sensors at key links of air separation equipment, oxygen storage tanks, and steelmaking equipment to ensure real-time monitoring of key parameters such as oxygen flow, pressure, and temperature. The sensors should be calibrated to ensure the accuracy and reliability of their measurement results. Select data acquisition equipment to receive the signals output by the sensors and convert them into digital data for storage and transmission. Configure the communication parameters of the data acquisition equipment to ensure smooth communication with the data center or server. Start the data acquisition equipment to ensure that it can receive the signals output by the sensors in real time and process them. Set the cycle and frequency of data acquisition to ensure the real-time and accuracy of the data. Store the collected data in the local storage device for subsequent analysis and processing. At the same time, upload part or all of the data to the data center or server for remote access and analysis.
[0028] The data acquisition equipment establishes a communication connection with the data center or server through wired or wireless means to ensure the stability and reliability of the communication connection and avoid loss or delay in the data transmission process. According to the requirements of the data center or server, the collected data is converted into a format such as JSON or XML to ensure the compatibility and readability of the data format, which is convenient for subsequent data processing and analysis. The converted data is uploaded to the data center or server, and the cycle and frequency of data upload are set to ensure the real-time and integrity of the data. During the upload process, data encryption and verification are performed to ensure the security and accuracy of the data.
[0029] After the data is uploaded, the uploaded data is verified, such as checking the integrity and accuracy of the data. For data that fails the verification, it is retransmitted or marked to ensure the reliability of the data. The uploaded data is compared and analyzed with historical data to verify the rationality and consistency of the data. For abnormal data or data that does not meet expectations, further analysis and processing are performed to ensure the accuracy and reliability of the data. The uploaded data is stored and managed, and a data warehouse or database is established to facilitate subsequent data analysis and application. The data is backed up and restored to ensure the security and recoverability of the data. The uploaded data is used for training and verification of intelligent prediction models to improve the accuracy of predictions. The data is used to monitor and optimize the production process to improve production efficiency and product quality. The data is used for fault warning and diagnosis to improve the reliability and safety of equipment.
[0030] Comprehensively collect historical oxygen supply and demand data from the data center. These data cover real-time monitoring information of oxygen flow, pressure, and temperature, as well as steelmaking production plans and equipment operation log-related data. Clean and integrate the collected data, remove duplicate, erroneous or invalid data, and pre-process the integrated data to lay a solid foundation for subsequent data analysis, so as to better meet the input requirements of the prediction model according to the characteristics of the data;
[0031] In-depth analysis of historical data to identify key factors affecting oxygen demand, Among them, S ot represents the oxygen supply and demand state value at time t, g(X) represents a function with input data X as the independent variable, F i (t) is the function of the i-th influencing factor with respect to time t, D i (x) is the data characteristic value of the i-th influencing factor, x represents the relevant data point, w i is the weight coefficient of the i-th influencing factor, E(t) is the error correction term, which is a function of time t. Based on these factors, valuable features are extracted from the data as input variables of the prediction model. According to the characteristics of the data and the prediction requirements, the algorithm is selected to build the oxygen demand prediction model. Among them, O pred (t) represents the predicted oxygen demand at time t, h represents a mapping function, θ j is the parameter vector related to the jth algorithm, A j (X, t) is the jth algorithm basis function based on data X and time t, ∈(t) is the error term, and the model is trained using the preprocessed data and extracted features. The model's prediction ability is improved by adjusting the model parameters and algorithm structure;
[0032] Use cross-validation, hold-out method or online learning method to verify the trained model and evaluate its prediction performance. According to the verification results, make necessary adjustments and optimizations to the model to improve its accuracy and generalization ability. Apply the optimized model to new data to predict oxygen demand in the future. σ(t)·Z, where O future (t) represents the predicted oxygen demand at future time t, The M in it represents a mapping function, which transforms the optimized parameter vector New data X new and the future time point t as input, f(t) is the time adjustment function, is the kth parameter obtained after model optimization, B k (X new ) is based on the new data X new The kth characteristic function, g k (t) is a time-dependent uncertainty measurement function, Z is a random variable that obeys a standard normal distribution, and the prediction result should include the predicted value and its confidence interval to reflect the uncertainty of the prediction;
[0033] Conduct in-depth analysis of the forecast results to understand the supply and demand changes and trends behind them, apply the forecast results to actual production scheduling and decision-making, guide the operation adjustment of air separation equipment and oxygen storage systems, and achieve a dynamic balance between oxygen supply and demand. As time goes by and new data is generated, the forecast model is regularly updated and maintained, new features and data sources are introduced, and the model structure and parameters are optimized to adapt to the ever-changing production environment and needs.
[0034] The dynamic scheduling module first receives the forecast data from the intelligent prediction module. These data include the expected oxygen demand in the future. The received forecast data are analyzed to clarify the oxygen demand and demand trend in different time periods. According to the analyzed forecast data, the dynamic scheduling module automatically adjusts the operating parameters of the oxygen production equipment to ensure that the oxygen production can match the predicted oxygen demand. The adjustment process may involve the coordinated control of multiple oxygen production equipment to achieve the optimal oxygen production efficiency. The current reserve information of the oxygen storage tank is obtained in real time through sensors or other monitoring means. The monitoring data is compared with the preset safety inventory standard to evaluate the adequacy of oxygen reserves.
[0035] According to the real-time monitored oxygen reserve data, the dynamic scheduling module optimizes the oxygen release strategy to avoid waste when there is excess oxygen. At the same time, it formulates and implements an oxygen replenishment plan to ensure that the reserve can be replenished in time when the oxygen demand peaks to avoid shortages. The dynamic scheduling module uniformly manages and schedules all equipment in the air substation area, and optimizes the overall resource allocation and improves resource utilization efficiency by coordinating the operation of various equipment. According to real-time demand and equipment status, the dynamic scheduling module automatically adjusts the operation mode and sequence of each device to ensure that they can work together to meet oxygen demand. Collaborative operation may involve load balancing and fault switching strategies between equipment to improve system reliability and stability;
[0036] Through the comprehensive implementation of the above steps, the dynamic scheduling module can significantly improve the reliability and efficiency of oxygen supply. Real-time monitoring and dynamic adjustment can ensure the timeliness and accuracy of oxygen supply to meet the actual needs of users.
[0037] The human-computer interaction module should first design an intuitive and easy-to-use user interface to ensure that operators can easily understand and operate. The interface should include a display area for real-time oxygen supply and demand data, forecast results, and dispatch instruction information, so that operators can check the system status at any time and obtain real-time oxygen supply and demand data from the system, including the current oxygen flow, pressure, temperature, and storage tank reserves. These data should be dynamically updated on the user interface so that operators can understand the system's operating status in real time.
[0038] Receive the output results of the intelligent prediction module, including the oxygen demand forecast for a period of time in the future, receive the dispatch instructions of the dynamic dispatch module, and clearly display these prediction results and dispatch instructions on the user interface so that operators can understand the future status and dispatch plan of the system. Provide an operation interface to allow operators to modify and optimize the system prediction and dispatch results according to actual conditions. Operators can adjust the operation of the system by entering new parameters or selecting different strategies;
[0039] After completing the correction and optimization, the operator confirms the modified content through the interface. The human-computer interaction module passes the confirmed modified content to the intelligent prediction module and the dynamic scheduling module so that the system can adjust according to the new instructions. The operator can provide feedback through the user interface. The human-computer interaction module collects this feedback and passes it to other modules of the system for continuous optimization and improvement.
[0040] Embodiment 2
[0041] A series of high-precision sensors have been carefully installed at key locations of air separation equipment, oxygen storage tanks and steelmaking equipment. These sensors can monitor key parameters such as oxygen flow, pressure, temperature, etc. in real time to ensure the accuracy and real-time nature of the data. Professional data acquisition equipment is configured to receive signals transmitted by sensors and convert them into data formats that can be used for analysis. At the same time, reasonable communication parameters are set to ensure stable communication between the data acquisition equipment and the data center. The data acquisition equipment automatically collects and stores data according to the set cycle and frequency. Before the data is uploaded to the data center, format conversion and encryption verification will be performed to ensure data compatibility and security. After uploading, the data will undergo further verification and validation and will eventually be stored in the data warehouse, providing strong support for subsequent intelligent prediction, production monitoring optimization, and fault warning diagnosis.
[0042] Using the historical oxygen supply and demand data stored in the data center, we conducted in-depth data cleaning, integration and preprocessing. By removing duplicate, erroneous or invalid data, we improved the quality and availability of the data. Based on the preprocessed data, we built an oxygen demand forecasting model. Among them, O pred (t) represents the predicted oxygen demand at time t, h represents a mapping function, θ j is the parameter vector related to the jth algorithm, A j (X, t) is the jth algorithm basis function based on data X and time t, ∈(t) is the error term. The model uses a machine learning algorithm to deeply explore the potential laws and trends in the data.
[0043] The forecasting model not only takes into account historical oxygen supply and demand data, but also combines real-time production data and equipment operation record information to achieve accurate forecasts of oxygen demand in the future. Among them, O future (t) represents the predicted oxygen demand at future time t, The M in it represents a mapping function, which transforms the optimized parameter vector New data X new and the future time point t as input, f(t) is the time adjustment function, is the kth parameter obtained after model optimization, B k (X new ) is based on the new data X new The kth characteristic function, g k (t) is a time-related uncertainty measurement function, Z is a random variable that obeys the standard normal distribution, and the prediction result includes the predicted value and its confidence interval, providing a reliable basis for subsequent dynamic scheduling.
[0044] According to the output results of the intelligent prediction module, the dynamic scheduling module can automatically adjust the operating parameters of the oxygen production equipment to match the predicted oxygen demand. This function ensures the timeliness and accuracy of the oxygen supply and effectively avoids the problem of insufficient or excessive oxygen supply. At the same time, the dynamic scheduling module also monitors the reserves of oxygen storage tanks in real time and compares them with the safety inventory standards. According to the comparison results, the module can optimize the oxygen release and replenishment strategy to ensure that the reserves of oxygen storage tanks always remain within a reasonable range. In addition, the dynamic scheduling module also integrates the overall resources of the air separation station area, realizes the coordinated operation of equipment, and improves the reliability and efficiency of oxygen supply through unified management and scheduling of all equipment.
[0045] An intuitive and easy-to-use user interface is designed to display real-time oxygen supply and demand data, forecast results and future scheduling instructions. The interface is dynamically updated, allowing users to clearly understand the current status and future needs of the system. An operation interface is provided to support manual intervention. Operators can correct and optimize system forecasts and scheduling results according to actual conditions. After completing the correction, the modification content is confirmed through the interface. The human-computer interaction module will pass the update to related modules to ensure continuous optimization and improvement of the system.
[0046] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.
Claims
1. A steel plant air separation station oxygen supply and demand balance control system, characterized in that: The system includes data acquisition module, intelligent prediction module, dynamic scheduling module and human-computer interaction module: The data acquisition module is equipped with high-precision sensors to monitor the oxygen flow, pressure, and temperature parameters of air separation equipment, oxygen storage tanks, and steelmaking equipment in real time, collect steelmaking production plans, equipment operation records, and historical oxygen supply and demand data, and provide data support for intelligent prediction; The intelligent prediction module: comprehensively collects historical oxygen supply and demand data from the data center, which covers real-time monitoring information of oxygen flow, pressure, and temperature, as well as steelmaking production plan and equipment operation log related data, cleans and integrates the collected data, and pre-processes the integrated data to lay a solid foundation for subsequent data analysis, so as to better adapt to the input requirements of the prediction model according to the characteristics of the data; In-depth analysis of historical data to identify key factors affecting oxygen demand, Among them, S ot represents the oxygen supply and demand state value at time t, g(X represents a function with input data X as independent variable, F i (t) is the function of the i-th influencing factor with respect to time t, D i (x) is the data characteristic value of the i-th influencing factor, x represents the relevant data point, w i is the weight coefficient of the i-th influencing factor, E(t) is the error correction term, which is a function of time t. Based on these factors, valuable features are extracted from the data as input variables of the prediction model. According to the characteristics of the data and the prediction requirements, the algorithm is selected to build the oxygen demand prediction model. The model is trained using the preprocessed data and the extracted features. The prediction ability of the model is improved by adjusting the model parameters and algorithm structure. Use cross-validation, hold-out method or online learning method to verify the trained model and evaluate its prediction performance. According to the verification results, make necessary adjustments and optimizations to the model to improve the accuracy and generalization ability of the model. Apply the optimized model to new data to predict the oxygen demand in the future. The prediction results should include the predicted value and its confidence interval to reflect the uncertainty of the prediction. Conduct in-depth analysis of the forecast results, understand the supply and demand changes and trends behind them, apply the forecast results to actual production scheduling and decision-making, guide the operation adjustment of air separation equipment and oxygen storage systems, and achieve a dynamic balance between oxygen supply and demand. As time goes by and new data is generated, regularly update and maintain the forecast model, introduce new features and data sources, and optimize the model structure and parameters to adapt to the ever-changing production environment and needs; The dynamic scheduling module: according to the output results of the intelligent prediction module, automatically adjusts the operating parameters of the oxygen production equipment to match the predicted oxygen demand, monitors the reserves of the oxygen storage tanks in real time, optimizes the oxygen release and replenishment strategies, avoids oxygen waste and shortage, integrates the overall resources of the air separation station area, realizes the coordinated operation of the equipment, and improves the reliability and efficiency of the oxygen supply; The human-computer interaction module provides a user-friendly interface, displays real-time oxygen supply and demand data, forecast results and dispatch instruction information, supports manual intervention and adjustment, and allows operators to modify and optimize system forecast and dispatch results according to actual conditions.
2. According to claim 1, a steel plant air separation station oxygen supply and demand balance control system is characterized in that: The data acquisition module is installed and calibrated in the oxygen supply and demand balance control system of the air separation station area of the steel plant, and high-precision sensors are installed on the air separation equipment, oxygen storage tanks and steelmaking equipment to monitor the oxygen flow, pressure and temperature parameters in real time. Then, the data acquisition equipment is configured to receive the sensor signal, and the communication parameters are set to ensure communication with the data center. After the data acquisition equipment is started, data is collected according to the set period and frequency, and stored locally and uploaded to the data center. The data needs to be formatted before uploading, and encrypted and checked during the transmission process to ensure security. After uploading, the data is checked and verified, and the data is stored and managed in the data warehouse, and applied to intelligent prediction, production monitoring optimization and fault warning diagnosis.
3. According to claim 1, a steel plant air separation station oxygen supply and demand balance control system is characterized in that: The intelligent prediction module selects an algorithm to build an oxygen demand prediction model: Among them, O pred (t) represents the predicted oxygen demand at time t, h represents a mapping function, θ j is the parameter vector associated with the jth algorithm, A j (X, t) is the jth algorithm basis function based on data X and time t, and ∈(t) is the error term.
4. According to claim 1, a steel plant air separation station oxygen supply and demand balance control system is characterized in that: The optimized model is applied to new data to predict oxygen demand in the future: Among them, O future (t) represents the predicted oxygen demand at future time t, The M in it represents a mapping function, which transforms the optimized parameter vector New data X new and the future time point t as input, f(t) is the time adjustment function, is the kth parameter obtained after model optimization, B k (X new ) is based on the new data X new The kth characteristic function, g k (t) is the time-dependent uncertainty measure function, and Z is a random variable that obeys the standard normal distribution.
5. The oxygen supply and demand balance control system for the air separation station area of a steel plant according to claim 1, characterized in that: The dynamic scheduling module receives the future oxygen demand forecast data provided by the intelligent prediction module and analyzes it to clarify the demand trend. Based on these data, the module automatically adjusts the operating parameters of the oxygen production equipment. By real-time monitoring of the reserves of oxygen storage tanks and comparing them with the safety inventory standards, the module can optimize the oxygen release and replenishment strategy to avoid waste and shortages.
6. The oxygen supply and demand balance control system for the air separation station area of a steel plant according to claim 5, characterized in that: The dynamic scheduling module integrates the overall resources of the air separation station area, uniformly manages and schedules all equipment, and automatically adjusts the equipment operation mode and sequence according to real-time demand and equipment status to achieve coordinated operation among equipment.
7. The oxygen supply and demand balance control system for the air separation station area of a steel plant according to claim 1, characterized in that: The human-computer interaction module is designed with an intuitive and easy-to-use user interface that displays real-time oxygen supply and demand data, forecast results and future scheduling instructions. The interface is dynamically updated and provides a clear understanding of the system's future needs and scheduling plans.
8. The oxygen supply and demand balance control system for the air separation station area of a steel plant according to claim 7, characterized in that: The human-computer interaction module provides an operation interface and supports manual intervention, allowing operators to modify and optimize system prediction and scheduling results according to actual conditions. After the modification is completed, the modified content is confirmed through the interface. The human-computer interaction module passes the update to related modules. The module collects operator feedback for continuous optimization and improvement of the system.