A monitoring system and management method for a steelmaking process

Abstract

A steelmaking process monitoring system, characterized in that it comprises an adaptive module, a process monitoring module, a composite recording module, an adjustment module, a feedback module and a process optimization module, wherein the process monitoring module comprises a first sensing module group and a second sensing module group; the adaptive module is used to record the steelmaking process flow; the first sensing module group comprises various gas sensors; the second sensing module group comprises various environmental sensors; the composite recording module is used to record and analyze the data recorded by the first sensing module group; the process optimization module is used to optimize the process according to the concentration change curve; the adjustment module is used to adjust the sensitivity of the second sensing module group; the feedback module is used to generate improvement strategies for the production process flow; by setting the adaptive module and integrating the process identification database, the flexibility and application range of the system are significantly improved, and the system is suitable for rapid switching and deployment of various steelmaking process flows.

Description

Technical Field

[0001] This invention relates to the field of steelmaking, and more particularly to a monitoring system and management method for steelmaking processes. Background Technology

[0002] In modern steel production, the steelmaking process is a crucial stage that determines steel quality, energy consumption, and environmental emissions. Traditional steelmaking processes primarily rely on manual experience for operation and control, supplemented by offline sampling and periodic testing to assess process status. However, these methods suffer from problems such as response lag, discontinuous data, and strong subjectivity, making it difficult to achieve real-time and accurate monitoring of complex and dynamic smelting processes.

[0003] With the development of smart manufacturing and industrial IoT technologies, some enterprises have begun to introduce sensor systems to monitor key parameters in the steelmaking process online. Existing monitoring systems mostly use fixed-configuration sensor networks, setting fixed sampling frequencies and analysis models for specific processes, lacking the ability to adaptively identify different steelmaking processes. Furthermore, traditional systems typically operate gas monitoring and environmental parameter monitoring independently, failing to achieve multi-source data fusion analysis, resulting in a single basis for judging process anomalies and a lack of systematic support for optimization suggestions.

[0004] For example, invention CN111912532A uses a fuzzy control algorithm to compensate for sensor output based on changes in temperature and humidity, but it is not combined with a specific production process model and does not have the ability to diagnose and optimize processes.

[0005] Therefore, there is an urgent need for an intelligent monitoring system for steelmaking processes that has adaptive recognition capabilities, multi-dimensional data fusion and analysis functions, and can realize dynamic sensor calibration and closed-loop process optimization, so as to improve the stability, energy efficiency and environmental compliance of the steelmaking process. Summary of the Invention

[0006] To achieve the above objectives, the present invention provides a monitoring system and management method for steelmaking processes, characterized in that it includes: The system includes an adaptive module, a process monitoring module, a composite recording module, an adjustment module, a feedback module, and a process optimization module, wherein the process monitoring module comprises a first sensing module group and a second sensing module group. The adaptive module is used to record the steelmaking process flow, the types of data that need to be detected in each process, and the corresponding data range; The first sensing module group includes various gas sensors for identifying changes in the concentration of various gases in the air caused by the process. The second sensing module group includes various environmental sensors for collecting environmental data that directly affects each process. The composite recording module is electrically connected to the first sensing module group and is used to record and analyze the data recorded by the first sensing module group and generate a concentration change curve. The process optimization module is electrically connected to the composite recording module and is used to optimize the process based on the concentration change curve. The adjustment module is electrically connected to the second sensing module group and is used to adjust the sensitivity of the second sensing module group according to the environmental data received by the second sensing module group and send the data to the feedback module. The feedback module is used to generate improvement strategies for the production process based on the results generated by the adjustment module, and to adjust the data range corresponding to different data types of the adaptive module according to the improvement strategies.

[0007] Furthermore, the adaptive module is also configured with a process identification database, which is used to automatically match the corresponding sensor activation combination, sampling strategy and process optimization model according to the manually input process name.

[0008] Furthermore, the adaptive module allows users to manually correct the input process information through the human-computer interaction interface, and triggers the system to reload the corresponding sensor configuration and analysis model, thereby realizing the system's adaptive modification function.

[0009] Furthermore, the first sensing module group includes a high-precision electrochemical sensor, an infrared gas analyzer, and a laser scattering dust detector, which are arranged at the gas outlet of the steelmaking furnace, the flue, and key ventilation locations in the workshop.

[0010] Furthermore, the second sensing module group includes a temperature sensor, a pressure transmitter, a humidity sensor, and an anemometer, used to collect the temperature, pressure, relative humidity, and airflow velocity of the furnace interior and surrounding environment in real time.

[0011] Furthermore, the composite recording module is used to further perform data correction processing, including: baseline drift correction of the original gas concentration data, periodic calibration using standard gas samples to compensate for sensor aging errors, and fusion of multi-source sensor data using a Kalman filter algorithm to reduce noise interference.

[0012] Furthermore, the process optimization module identifies whether there is a risk of insufficient reaction, excessive oxidation, or excessive emissions in the current process based on the peak occurrence time, slope, and fluctuation amplitude in the concentration change curve, and generates corresponding optimization instructions.

[0013] Furthermore, the adjustment module incorporates a fuzzy control algorithm to dynamically adjust the response threshold and signal amplification factor of the second sensing module group based on ambient temperature, humidity, and airflow disturbance, thereby improving detection stability and accuracy under complex working conditions.

[0014] Furthermore, the feedback module updates the data types and standard data ranges of the corresponding processes in the adaptive module in reverse according to the monitoring effect after the actual implementation of the improvement strategy, so as to realize the system's self-learning ability based on historical experience.

[0015] A method for monitoring a steelmaking process, characterized by comprising the following steps: S1. Adaptive Configuration Phase: The adaptive module receives the current steelmaking process type input by the user and calls the pre-stored detection data types and their standard data ranges corresponding to the process; wherein, the detection data types include gas concentration parameters and environmental process parameters; S2. Sensor startup and data acquisition phase: Start the first and second sensing module groups that match the process; The first sensor module group collects real-time data on CO, CO2, SO2, and NO levels in the air due to the changes in the manufacturing process. x And data on changes in the concentration of particulate matter; The second sensing module group synchronously collects furnace temperature, pressure, humidity, and airflow velocity as environmental data that directly affects the execution of the process; S3. Data recording and correction processing stage: The raw gas concentration data collected by the first sensing module group is transmitted to the composite recording module for time alignment and normalization processing, and data correction is performed, including baseline drift correction, periodic calibration compensation, and fusion of multi-source data using Kalman filtering algorithm to generate a high-precision multi-dimensional concentration change curve. S4. Process Status Analysis and Optimization Stage: Based on the peak occurrence time, slope and fluctuation amplitude of the concentration change curve, the process optimization module identifies whether there is a risk of insufficient reaction, excessive oxidation or excessive emissions in the current process, and generates process parameter optimization suggestions in combination with the historical best process model; S5. Dynamic sensitivity adjustment stage: The adjustment module dynamically adjusts the sampling frequency, response threshold and signal amplification factor of the second sensing module group based on the ambient temperature and humidity and airflow disturbance level collected by the second sensing module group, using the built-in fuzzy control algorithm to improve the detection stability under complex working conditions; S6. Feedback closed loop and strategy generation stage: The feedback module integrates the process optimization suggestions and sensor adjustment results to generate process flow improvement strategies for feeding rate, oxygen supply intensity and temperature rise curve, and automatically sends the strategy to the PLC control system to realize closed-loop control of the production process; S7. Self-learning and updating phase: Based on the monitoring results after the actual implementation of the improvement strategy, the data types and standard data ranges of the corresponding processes in the adaptive module are updated in reverse to realize the system's adaptive learning and continuous optimization for different working conditions.

[0016] Due to the adoption of the above technical solution, the technical progress achieved by this invention includes the following aspects: 1. By setting up an adaptive module and integrating a process identification database, the system can automatically match the corresponding sensor activation combination, sampling strategy and process optimization model according to the manually input process name, avoiding the tedious manual configuration process in traditional systems, significantly improving the system's flexibility and applicability, and making it suitable for the rapid switching and deployment of various steelmaking processes. 2. Achieve dynamic adaptive adjustment of the sensor. The adjustment module has a built-in fuzzy control algorithm, which can adjust the response threshold and signal amplification factor of the second sensor module group in real time according to the ambient temperature, humidity and airflow disturbance. It can dynamically optimize the sampling frequency and sensitivity, maintain high-precision detection capability under complex and harsh working conditions, and extend the service life of the equipment. 3. Possesses continuous learning and evolution capabilities: By updating the data types and standard data ranges corresponding to each process in the adaptive module through the feedback module, the system can accumulate experience after multiple runs, continuously optimize its own parameter configuration and judgment logic, and has the self-learning ability based on historical data to adapt to changes in different production lines, raw materials and operating habits. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a structural diagram of the monitoring system of the present invention; Figure 2 This is a flowchart illustrating the management method steps of the present invention; Figure 3 This is a diagram illustrating the data correction steps in an embodiment of the present invention; Figure 4 This is a flowchart illustrating the identification and configuration process of the adaptive module in an embodiment of the present invention. Figure 5 This is a schematic diagram of closed-loop linkage according to an embodiment of the present invention; Detailed Implementation The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, in the following description, specific details such as particular system structures and technologies are set forth for illustrative purposes rather than for limiting purposes, in order to provide a thorough understanding of the embodiments of the present invention. However, those skilled in the art should understand that the present invention can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary details.

[0019] Example 1 According to the instruction manual Figures 1 to 2 It can be seen that this embodiment is an example of the use of a monitoring system and management method for a steelmaking process, specifically including: an adaptive module, a process monitoring module, a composite recording module, an adjustment module, a feedback module, and a process optimization module, wherein the process monitoring module includes a first sensing module group and a second sensing module group; The adaptive module records the steelmaking process flow, the types of data to be detected in each process, and the corresponding data ranges. It also includes a process identification database to automatically match the corresponding sensor activation combinations, sampling strategies, and process optimization models based on manually input process names. The adaptive module allows users to manually correct entered process information through a human-machine interface, triggering the system to reload the corresponding sensor configurations and analysis models, thus enabling the system's adaptive modification function.

[0020] The first sensing module group includes various gas sensors used to identify changes in the concentration of various gases in the air caused by the process. The first sensing module group includes a high-precision electrochemical sensor, an infrared gas analyzer, and a laser scattering dust detector, which are arranged at the gas outlet of the steelmaking furnace, the flue, and key ventilation locations in the workshop.

[0021] The second sensing module group includes various environmental sensors to collect environmental data that directly affects each process. The second sensing module group includes temperature sensors, pressure transmitters, humidity sensors and anemometers to collect temperature, pressure, relative humidity and airflow speed in and around the furnace in real time.

[0022] The composite recording module is electrically connected to the first sensing module group and is used to record and analyze the data recorded by the first sensing module group and generate a concentration change curve. The composite recording module is used to further perform data correction processing, including: baseline drift correction of the original gas concentration data, periodic calibration using standard gas samples to compensate for sensor aging errors, and fusion of multi-source sensor data using a Kalman filter algorithm to reduce noise interference.

[0023] The process optimization module, electrically connected to the composite recording module, is used to optimize the process based on the concentration change curve. Based on the peak occurrence time, slope, and fluctuation amplitude in the concentration change curve, the process optimization module identifies whether there is a risk of insufficient reaction, excessive oxidation, or excessive emissions in the current process, and generates corresponding optimization instructions.

[0024] The adjustment module, electrically connected to the second sensor module group, is used to adjust the sensitivity of the second sensor module group based on the environmental data received by the second sensor module group and send the data to the feedback module. The adjustment module has a built-in fuzzy control algorithm to dynamically adjust the response threshold and signal amplification factor of the second sensor module group according to the ambient temperature, humidity and airflow disturbance, thereby improving the detection stability and accuracy under complex working conditions.

[0025] The feedback module generates improvement strategies for the production process based on the results produced by the adjustment module, and adjusts the data ranges corresponding to different data types in the adaptive module according to the improvement strategies. The feedback module integrates adjustment logs and process optimization suggestions into a visual report, pushes it to the operation terminal, and supports automatic distribution to the PLC control system for adjusting the feeding rate, oxygen supply intensity, and temperature rise curve. Based on the monitoring results after the actual implementation of the improvement strategies, the feedback module updates the data types and their standard data ranges for the corresponding processes in the adaptive module, enabling the system to learn from historical experience.

[0026] A method for monitoring a steelmaking process, characterized by comprising the following steps: S1. Adaptive Configuration Phase: The adaptive module receives the current steelmaking process type input by the user and calls the pre-stored detection data types and their standard data ranges corresponding to the process; among which, the detection data types include gas concentration parameters and environmental process parameters; S2. Sensor startup and data acquisition phase: Start the first and second sensor module groups that match the process; The first sensing module group collects real-time data on CO, CO2, SO2, and NO levels in the air due to changes in the process flow. x And data on changes in the concentration of particulate matter; The second sensing module group synchronously collects furnace temperature, pressure, humidity, and airflow velocity as environmental data that directly affects the execution of the process; S3. Data recording and correction stage: The raw gas concentration data collected by the first sensor module group is transmitted to the composite recording module for time alignment and normalization, and data correction is performed, including baseline drift correction, periodic calibration compensation, and fusion of multi-source data using Kalman filtering algorithm to generate a high-precision multi-dimensional concentration change curve. S4. Process Status Analysis and Optimization Stage: Based on the peak occurrence time, slope and fluctuation range in the concentration change curve, the process optimization module identifies whether there is a risk of insufficient reaction, excessive oxidation or excessive emissions in the current process, and generates process parameter optimization suggestions in combination with the historical best process model; S5. Dynamic Sensitivity Adjustment Stage: The adjustment module dynamically adjusts the sampling frequency, response threshold, and signal amplification factor of the second sensor module group based on the ambient temperature, humidity, and airflow disturbance level collected by the second sensor module group, using the built-in fuzzy control algorithm to improve the detection stability under complex working conditions. S6. Feedback closed loop and strategy generation stage: The feedback module integrates process optimization suggestions and sensor adjustment results to generate process improvement strategies for feeding rate, oxygen supply intensity and temperature rise curve, and automatically sends the strategy to the PLC control system to realize closed-loop control of the production process. S7. Self-learning and updating phase: Based on the monitoring results after the actual implementation of the improvement strategy, the data types and standard data ranges of the corresponding processes in the adaptive module are updated in reverse to realize the system's adaptive learning and continuous optimization for different working conditions.

[0027] The overall effect achieved in Example 1 is as follows: By separating the limb fixation ring from the pressure ring, the function of the pressure hemostasis device is achieved. While realizing the functions of the existing pressure hemostasis device, the multiple limb fixation rings reduce the probability of limb movement and facilitate medical staff's observation of the puncture site.

[0028] Example 2 According to the instruction manual Figure 3 As can be seen, this embodiment demonstrates how the composite recording module of this invention significantly improves the accuracy and stability of monitoring results in complex industrial environments by performing multiple corrections on the original gas concentration data. A converter workshop has long suffered from large fluctuations in CO concentration and frequent alarms, suspected to be caused by sensor drift or environmental interference. Therefore, the monitoring system described in this invention was introduced to verify its data correction capabilities.

[0029] In the initial stage of system operation, the high-precision electrochemical CO sensor in the first sensing module group, located near the gas outlet of the steelmaking furnace, showed a slow upward trend in CO concentration, remaining at around 80 ppm even during furnace shutdown, initially indicating baseline drift. Simultaneously, the infrared gas analyzer measured the CO2 concentration at the same location as stable within the normal range of <0.5%, indicating that it was not a real gas leak.

[0030] After receiving the raw data, the composite recording module first performs time alignment and normalization to ensure that all sensor data have a unified time reference. Then, it initiates three key correction steps: First, it uses a sliding window averaging method to subtract the zero-point offset, identifying that the electrochemical sensor's zero point has drifted by approximately 60 ppm, and corrects for this. Second, it uses a standard gas sample containing a precise concentration of 100 ppm CO, automatically injected every two hours, for periodic calibration compensation to correct sensitivity decay. Third, it applies a Kalman filter algorithm to fuse the electrochemical and infrared dual-source data, weighting and outputting the optimal estimate during the dynamic process, effectively suppressing random noise interference.

[0031] After 72 hours of continuous comparative testing, it was found that the correlation coefficient between the corrected CO concentration curve and the results detected by the third-party mass spectrometer reached over 0.98, and the maximum absolute error decreased from ±45 ppm to within ±8 ppm. In particular, during the peak blowing stage, the system successfully captured the CO peak at 5 minutes and 18 seconds, with a clearly discernible slope of change, unaffected by instantaneous smoke and dust disturbances.

[0032] The overall effect of Example 2 is as follows: This example demonstrates that the present invention significantly improves the accuracy and long-term stability of gas concentration monitoring through baseline drift correction, periodic calibration compensation and multi-source sensor data fusion, overcomes measurement deviations caused by sensor aging, environmental temperature changes and noise interference, and ensures the reliability of the data foundation for process diagnosis and optimization decisions.

[0033] Example 3 According to the instruction manual Figure 4 This embodiment illustrates how the present invention achieves automatic identification and configuration matching of different steelmaking processes through an adaptive module and a process identification database. A large integrated steel enterprise adopts a parallel production mode with multiple production lines, requiring frequent switching between various processes such as converter blowing, LF refining, and RH vacuum degassing. Traditional monitoring systems require technicians to manually activate the corresponding sensor groups, set the sampling frequency, and load the analysis model each time a production line changes, which is time-consuming and prone to errors. Therefore, the present invention deploys an intelligent monitoring system with adaptive capabilities.

[0034] During the system initialization phase, engineers pre-entered information on three main process categories into the process identification database in the adaptive module via a human-machine interface. Each process category includes: the types of data to be detected, such as gas parameters (CO / CO2 / SO2 concentration), environmental parameters (temperature / pressure / humidity), standard data ranges (e.g., LF furnace temperature range of 1500–1600°C), corresponding sensor activation combinations (e.g., dust monitors need to be turned off during the RH process to prevent false triggering), recommended sampling strategies (1Hz high-frequency sampling during the blowing period, reduced to 0.2Hz for energy-saving operation during the refining period), and the binding of dedicated process optimization models, such as decarbonization rate prediction models based on reaction kinetics.

[0035] When the operator selects "LF Refining" as the upcoming process on the control terminal, the adaptive module immediately retrieves the complete configuration scheme for that process from the database and automatically sends instructions to the process monitoring module. The system then activates the electrochemical SO2 sensor and infrared CO2 analyzer in the first sensor module group, while simultaneously activating the high-temperature thermocouple and micro-pressure transmitter in the second sensor module group. The composite recording module loads Kalman filter parameters suitable for the refining stage, and the process optimization module switches to the "inclusion flotation efficiency evaluation model." The entire process requires no manual intervention, with a response time of less than 3 seconds.

[0036] If subsequent processes are changed to "RH vacuum treatment," the system automatically switches configurations again: unnecessary humidity sensors are shut down to prevent failure due to the high vacuum environment, the gas sampling pump flow rate is adjusted to adapt to low-pressure conditions, and a dedicated emission warning algorithm for low-oxygen control is activated. This mechanism significantly improves the system's flexibility and applicability, making it particularly suitable for modern steel plants producing multiple varieties in small batches.

[0037] The overall effect of Embodiment 3 is as follows: This embodiment verifies that the present invention, through the collaborative work of the adaptive module and the process identification database, can automatically match sensor combinations, sampling strategies and analysis models according to the process name input by the user, realizing fast, accurate and unmanned configuration switching across processes, avoiding the cumbersome manual setting process in traditional systems, and greatly improving production preparation efficiency and system intelligence level.

[0038] Example 4 According to the instruction manual Figure 5 As can be seen, this embodiment illustrates how the present invention achieves the system's self-learning and updating function based on historical experience through closed-loop linkage between the feedback module and the adaptive module. Before trialing this monitoring system, a steel plant's converter endpoint carbon temperature hit rate was only 82%, often resulting in rework due to excessive or insufficient oxygen supply. After the system went online, it gradually accumulated data on the effectiveness of optimization strategies, driving the continuous evolution of its parameters.

[0039] In the initial stage, the process optimization module suggested, based on a preset model, that "when the CO drop rate is <-1.5% / min, extend the strong blowing time by 10 seconds." After the first application, the PLC control system delayed the lance lifting accordingly, but the excess heat at the endpoint was too high, resulting in increased energy consumption. The system recorded this "optimization failure" case and marked it as a negative sample. In another operation, the system suggested "increasing the lance height + reducing the oxygen flow rate." After actual execution, the endpoint carbon content met the standard and the molten steel temperature was ideal, and this was marked as a positive success case.

[0040] After accumulating data from 20 consecutive heats, the feedback module analysis revealed that the original model was too aggressive when the silicon content of the raw hot metal was >0.5%. Therefore, the standard data range for the "High-Silicon Hot Metal Blowing" subcategory in the adaptive module was automatically updated—its CO decrease slope warning threshold was adjusted from -1.5% / min to -1.8% / min, and the recommended control strategy library was updated simultaneously. Subsequently, the hit rate of optimization suggestions under similar operating conditions increased to over 95%.

[0041] Furthermore, the system supports packaging such experiences into "localized knowledge packages," which can be imported and used by other production lines to form an enterprise-level accumulation of process knowledge.

[0042] The overall effect of Example 4 is as follows: This example verifies that the present invention can not only complete a single optimization task, but also reverse correct the data type definition and standard parameter range in the adaptive module according to the actual execution results, realize self-learning and continuous optimization capabilities based on historical experience, make the system more and more intelligent as the running time increases, adapt to changes in different raw materials, equipment status and operating habits, and have true "evolution" characteristics.

[0043] Example 5 This embodiment illustrates how the present invention improves the detection stability and accuracy under drastically fluctuating conditions by adjusting the built-in fuzzy control algorithm of the module to dynamically adjust the response thresholds, signal amplification factors, and sampling frequencies of various environmental sensors in the second sensing module group based on real-time collected ambient temperature, humidity, and airflow disturbance levels. A steel company located in a southern coastal region experiences high temperatures and humidity in summer, and frequent start-ups and shutdowns of the workshop ventilation system, leading to drastic changes in environmental parameters around the furnace area. Traditional fixed-parameter sensors often experience false alarms or data distortion. Therefore, the monitoring system described in this invention was deployed for technical verification.

[0044] During an LF refining operation, the workshop air conditioning suddenly malfunctioned, causing the ambient temperature to rise rapidly from the normal 26°C to 42°C, and the relative humidity to surge from 60% RH to 83% RH. Simultaneously, the exhaust fan activated due to automatic frequency adjustment, causing the airflow velocity in the flue to suddenly increase from a stable 7.5 m / s to 21.3 m / s, resulting in significant airflow disturbance. At this time, the output signals of the K-type thermocouple and piezoresistive pressure transmitter installed near the furnace cover showed significant fluctuations: temperature readings jumped by ±15°C, and the pressure signal exhibited high-frequency oscillations. The initial assessment was that this was measurement noise caused by environmental interference.

[0045] The system's adjustment module receives raw data from the second sensor module group in real time and initiates a built-in fuzzy control algorithm for analysis. This algorithm uses temperature change rate, humidity gradient, and wind speed standard deviation as input variables, and response threshold, signal amplification factor, and sampling frequency as output variables, making inference decisions based on a preset fuzzy rule base. For example, when the system detects humidity > 80% RH and wind speed change > 10 m / s, it triggers the following control logic: Lower the response threshold of the pressure transmitter by 12% to avoid triggering false alarms due to minor fluctuations; Increase the gain of the signal amplification circuit by 1.25 times to enhance the ability to capture weak signals; The sampling frequency was temporarily increased from 1 Hz to 2 Hz so that subsequent filtering processing could obtain more complete dynamic features.

[0046] After adjustment, the pressure data stabilized, effectively suppressing high-frequency noise. Simultaneously, the system automatically generated a log of the adjustment process and uploaded it to the composite record module for subsequent analysis. Throughout the entire period of the anomaly, no false alarms occurred, and the process optimization module was still able to make normal judgments based on reliable data.

[0047] In addition, after the environment returns to normal, the adjustment module re-evaluates the parameter stability and gradually reverts the sensor configuration to the default value to avoid overcompensation affecting long-term accuracy.

[0048] The overall effect of Embodiment 5 is as follows: This embodiment fully verifies that by introducing a fuzzy control algorithm, the present invention achieves intelligent and adaptive adjustment of the working parameters of the second sensing module group. It can effectively improve the anti-interference capability and measurement reliability of the sensor in complex industrial environments such as high temperature, high humidity, and strong airflow disturbance, and ensure the continuous and stable operation of the entire monitoring system. It is especially suitable for actual production sites with changing environmental conditions and is significantly better than traditional fixed parameter sensor systems.

[0049] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A monitoring system for a steelmaking process, characterized in that, include: The system includes an adaptive module, a process monitoring module, a composite recording module, an adjustment module, a feedback module, and a process optimization module, wherein the process monitoring module comprises a first sensing module group and a second sensing module group. The adaptive module is used to record the steelmaking process flow, the types of data that need to be detected in each process, and the corresponding data range; The first sensing module group includes various gas sensors for identifying changes in the concentration of various gases in the air caused by the process. The second sensing module group includes various environmental sensors for collecting environmental data that directly affects each process. The composite recording module is electrically connected to the first sensing module group and is used to record and analyze the data recorded by the first sensing module group and generate a concentration change curve. The process optimization module is electrically connected to the composite recording module and is used to optimize the process based on the concentration change curve. The adjustment module is electrically connected to the second sensing module group and is used to adjust the sensitivity of the second sensing module group according to the environmental data received by the second sensing module group and send the data to the feedback module. The feedback module is used to generate improvement strategies for the production process based on the results generated by the adjustment module, and to adjust the data range corresponding to different data types of the adaptive module according to the improvement strategies.

2. The monitoring system for the steelmaking process according to claim 1, characterized in that, The adaptive module is also equipped with a process identification database, which is used to automatically match the corresponding sensor activation combination, sampling strategy and process optimization model according to the process name entered manually.

3. The monitoring system for the steelmaking process according to claim 2, characterized in that, The adaptive module allows users to manually correct the input process information through the human-computer interaction interface and triggers the system to reload the corresponding sensor configuration and analysis model, thereby realizing the system's adaptive modification function.

4. The monitoring system for the steelmaking process according to claim 1, characterized in that, The first sensing module group includes a high-precision electrochemical sensor, an infrared gas analyzer, and a laser scattering dust detector, which are arranged at the gas outlet of the steelmaking furnace, the flue, and key ventilation locations in the workshop.

5. The monitoring system for the steelmaking process according to claim 1, characterized in that, The second sensing module group includes a temperature sensor, a pressure transmitter, a humidity sensor, and an anemometer, used to collect the temperature, pressure, relative humidity, and airflow velocity of the furnace interior and surrounding environment in real time.

6. The monitoring system for the steelmaking process according to claim 1, characterized in that, The composite recording module is used to further perform data correction processing, including: baseline drift correction of the original gas concentration data, periodic calibration using standard gas samples to compensate for sensor aging errors, and fusion of multi-source sensor data using a Kalman filter algorithm to reduce noise interference.

7. The monitoring system for the steelmaking process according to claim 1, characterized in that, The process optimization module identifies whether there is a risk of insufficient reaction, excessive oxidation, or excessive emissions in the current process based on the peak occurrence time, slope, and fluctuation amplitude in the concentration change curve, and generates corresponding optimization instructions.

8. The monitoring system for the steelmaking process according to claim 1, characterized in that, The adjustment module incorporates a fuzzy control algorithm to dynamically adjust the response threshold and signal amplification factor of the second sensing module group based on ambient temperature, humidity, and airflow disturbance, thereby improving detection stability and accuracy under complex working conditions.

9. The monitoring system for the steelmaking process according to claim 1, characterized in that, The feedback module updates the data types and standard data ranges of the corresponding processes in the adaptive module in reverse according to the monitoring effect after the actual implementation of the improvement strategy, so as to realize the system's self-learning ability based on historical experience.

10. A method for monitoring a steelmaking process, characterized in that, Includes the following steps: S1. Adaptive Configuration Phase: The adaptive module receives the current steelmaking process type input by the user and calls the pre-stored detection data types and their standard data ranges corresponding to the process; wherein, the detection data types include gas concentration parameters and environmental process parameters; S2. Sensor startup and data acquisition phase: Start the first and second sensing module groups that match the process; The first sensor module group collects real-time data on CO, CO2, SO2, and NO levels in the air due to the changes in the manufacturing process. x And data on changes in the concentration of particulate matter; The second sensing module group synchronously collects furnace temperature, pressure, humidity, and airflow velocity as environmental data that directly affects the execution of the process; S3. Data recording and correction processing stage: The raw gas concentration data collected by the first sensing module group is transmitted to the composite recording module for time alignment and normalization processing, and data correction is performed, including baseline drift correction, periodic calibration compensation, and fusion of multi-source data using Kalman filtering algorithm to generate a high-precision multi-dimensional concentration change curve. S4. Process Status Analysis and Optimization Stage: Based on the peak occurrence time, slope and fluctuation amplitude of the concentration change curve, the process optimization module identifies whether there is a risk of insufficient reaction, excessive oxidation or excessive emissions in the current process, and generates process parameter optimization suggestions in combination with the historical best process model; S5. Dynamic sensitivity adjustment stage: The adjustment module dynamically adjusts the sampling frequency, response threshold and signal amplification factor of the second sensing module group based on the ambient temperature and humidity and airflow disturbance level collected by the second sensing module group, using the built-in fuzzy control algorithm to improve the detection stability under complex working conditions; S6. Feedback closed loop and strategy generation stage: The feedback module integrates the process optimization suggestions and sensor adjustment results to generate process flow improvement strategies for feeding rate, oxygen supply intensity and temperature rise curve, and automatically sends the strategy to the PLC control system to realize closed-loop control of the production process; S7. Self-learning and updating phase: Based on the monitoring results after the actual implementation of the improvement strategy, the data types and standard data ranges of the corresponding processes in the adaptive module are updated in reverse to realize the system's adaptive learning and continuous optimization for different working conditions.

Images