Empty ladle correction method of steelmaking tank folding molten iron metering system

Abstract

The invention relates to the technical field of metallurgical engineering, and discloses an empty ladle correction method for a steelmaking tank folding molten iron metering system, which comprises the following steps of: S1, automatically carrying out comprehensive self-inspection when the system is started, and when the self-inspection is finished, taking empty ladles with the same model and specification as those in production from system records; s2, an operator hoists an empty ladle through automatic hoisting equipment, the weight of the empty ladle is recorded through a sensor, and multiple times of continuous measurement are carried out; and S3, automatically calculating an average value of multiple measurement results by the system, and comparing the average value with historical data. Through the automation function and the sensor of the system, manual operation errors and measurement errors are reduced, the accuracy and repeatability of data are guaranteed, the method is crucial to meeting strict quality control standards and reducing waste materials in the production process, automatic measurement and data processing reduce the requirements for manual intervention, the correction process is accelerated, and the production efficiency is improved. Production preparation time is shortened, and operation efficiency of a production line is improved.

Description

Technical Field

[0001] The invention relates to the technical field of metallurgical engineering, in particular to an empty ladle correction method for a steelmaking folding pot molten iron metering system. Background Art

[0002] In the steel production process, accurate molten iron metering directly affects the quality and cost of the product. The traditional steelmaking folding pot molten iron metering system mainly relies on mechanical scales and manual data recording for operation. The traditional steelmaking folding pot molten iron metering system usually includes a hook scale to measure the weight of the ladle filled with molten iron, so as to calculate the net weight of the molten iron.

[0003] Traditional steelmaking folding tank molten iron metering requires many manual steps, resulting in low efficiency and inability to meet rapid production requirements. The lack of an effective data integration and management system makes it impossible to monitor and analyze production data in real time, which in turn affects the timeliness and accuracy of decision-making. At the same time, traditional systems cannot adapt to rapid changes in the production environment. Fluctuations in temperature and pressure will reduce the accuracy of measurement data, affecting product quality and cost.

[0004] Therefore, those skilled in the art provide an empty ladle correction method for a steelmaking folding tank molten iron metering system to solve the problems raised in the above background technology. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides an empty ladle correction method for a steelmaking folding can molten iron metering system, which solves the problem that traditional steelmaking folding can molten iron metering requires many links of manual participation, resulting in low efficiency and inability to meet rapid production requirements, and lacks an effective data integration and management system, resulting in the inability to monitor and analyze data in production in real time, thereby affecting the timeliness and accuracy of decision-making.

[0006] To achieve the above purpose, the present invention is implemented by the following technical scheme: an empty ladle correction method of a steelmaking folding tank molten iron metering system, comprising the following steps:

[0007] S1. When the system is started, it will automatically conduct a comprehensive self-check. When the self-check is completed, an empty package of the same model and specification as that in production will be taken from the system record;

[0008] S2. The operator lifts the empty bag through the automated lifting equipment, and the sensor records the weight of the empty bag and performs multiple measurements continuously;

[0009] S3. The system automatically calculates the average value of multiple measurement results and compares it with historical data;

[0010] S4, the system automatically uploads the measurement data to the central database;

[0011] S5. The system uses machine learning algorithms to analyze the sources of errors in the measurement data, make correction suggestions, and correct the parameters according to the algorithm formula;

[0012] S6. Execute the automated test program to simulate the molten iron loading process and verify the accuracy after correction;

[0013] S7. The system automatically performs empty package correction regularly without manual intervention;

[0014] S8. The system uses the collected operation data for predictive maintenance, automatically schedules maintenance tasks, and reduces downtime;

[0015] S9. The system has monitoring functions and can automatically record operations and modifications for auditing and tracing.

[0016] Self-check in S1 can timely discover and repair potential faults, reducing production delays caused by equipment problems; S2 helps to obtain accurate and consistent data, providing a basis for subsequent data analysis and correction; S3 helps to detect whether there is systematic deviation or drift in the system and make timely adjustments; S4 provides support for data storage, backup and further analysis, and at the same time, guarantees the transparency and traceability of system operation; S5 step is an important point to improve measurement accuracy and system intelligence; S6 ensures that the calibrated system can accurately reflect the actual operation situation; S7 does not require manual intervention, improves the system maintenance efficiency and reduces problems caused by human errors; S8 helps to reduce sudden downtime and extend equipment life, reduce maintenance costs and improve production efficiency; S9 enhances the safety and compliance of the system.

[0017] Preferably, in said S1, the implementation steps of the system self-check are:

[0018] Hardware check: The system checks the connection status and functionality of the connected hardware devices to ensure there is no physical damage or connection errors;

[0019] Software verification: The system checks that its internal software components are intact and that software updates and patches have been installed;

[0020] Sensor calibration: Check the calibration status of the sensor to ensure the accuracy of sensor data;

[0021] Communication test: The system performs internal and external communication tests to ensure that data can be transmitted between system components;

[0022] Performance test: System operation performance test, simulating the operation process of hot metal metering in steelmaking folding tanks, and checking whether the processing speed and response time meet the expected standards;

[0023] Security check: Perform system security checks to ensure that the system is protected from unauthorized access and security threats;

[0024] Backup status verification: Check the backup status of system data to ensure that the backup data can be restored in time.

[0025] The purpose of hardware inspection is to ensure that the connected hardware devices have no physical damage and are connected correctly, so as to prevent data errors or system downtime caused by hardware failure; software verification helps to prevent software defects and security vulnerabilities, and improve the stability and security of the system; sensor calibration can improve the measurement accuracy of the system; communication testing must ensure that data can be effectively transmitted between different components of the system; performance testing must ensure that the system can run efficiently and stably in actual operation; security inspection protects system data from external intrusion and ensures the security of the operating environment; the backup status verification step is an important part of data protection to prevent data loss.

[0026] Preferably, in S3, the calculation formula of the average value is: Among them, x i represents the empty bag weight measured for the i-th time, and n is the number of measurements.

[0027] Preferably, in S4, the central database includes a database management system, a data storage module, a data model module, an access control module, and an interface; the database management system is responsible for the storage, query, update, and management of data; the data storage module is used to store data; the data model module is used to define the structure of data; the access control module is used to manage the authority to access the database; the interface is used to provide an interface for interacting with the system or application, allowing remote query and management.

[0028] The database management system is responsible for optimizing query efficiency, handling transaction management, and supporting data access control in a multi-user environment; the data storage module ensures that data is securely stored and can be efficiently retrieved and modified; the data model module can improve data organization efficiency and access speed through reasonable data model design; the access control module supports setting different access levels and roles, and assigning different data operation permissions to different users or user groups; the existence of interfaces makes the system highly scalable and flexible, and supports the integration of new applications or services.

[0029] Preferably, in S5, the implementation steps of analyzing the error sources of the measurement data and proposing correction suggestions by using a machine learning algorithm are as follows:

[0030] Collect historical measurement data;

[0031] Mark the relevant information of environmental conditions and equipment status for each measurement;

[0032] Extract features of historical data related to measurement errors;

[0033] Machine learning algorithms based on data characteristics are used to model and analyze sources of measurement error;

[0034] Train machine learning models using historical data to predict the relationship between measurement error and various features;

[0035] Analyze the results of the model to determine the degree of influence of each feature on the measurement error and make correction suggestions based on the analysis results;

[0036] Adjust system parameters according to the correction suggestions and determine the specific implementation steps of the correction parameters;

[0037] Run the calibrated system and collect new measurement data. At the same time, regularly monitor system performance to ensure that the calibration effect continues to be stable.

[0038] As the training basis for machine learning models, the collected historical data provides information for model learning and understanding of system behavior; by labeling data, it helps to accurately identify the source of errors; feature extraction is a key step in machine learning, and suitable features can significantly improve the prediction accuracy of the model and the effectiveness of correlation analysis; training models is the core of realizing prediction functions; model analysis reveals how each feature affects errors, and can provide targeted corrective measures based on data-driven insights to improve measurement accuracy; implementing corrective measures is the process of converting analysis into actual operations, and by adjusting system parameters, the accuracy of measurements can be actually improved; collecting new measurement data and regularly monitoring system performance are important steps to ensure the continued stability of the corrective measures, which helps to promptly discover new problems or opportunities for further optimization.

[0039] Preferably, in S5, the machine learning algorithm includes linear regression, logistic regression, and support vector machine;

[0040] The linear regression: y = β0 + β1x1 + β2x2 + ... + β n x n +∈, where y is the predicted value, β0,β1,...,β n are the model parameters, x1,x2,...,x n is the characteristic variable, ∈ is the error term;

[0041] The logistic regression:

[0042] Among them, p(y=1|x) is the probability of output being 1 under the condition of input x, β0,β1,...,β n are model parameters;

[0043] The support vector machine:

[0044] subject toys i(w·x i -b)≥1-ξ i ,fori=1,2,...,n,ξ i ≥0,fori=1,2,...,n,

[0045] Where w is the weight vector, b is the bias, ξ i is the slack variable and C is the penalty parameter.

[0046] Preferably, in S6, the implementation steps of executing the automated testing program are:

[0047] Prepare simulated hot metal loads for testing and, if practicable, use actual hot metal or equivalent test material;

[0048] Configure the test environment to simulate actual hot metal loading conditions and ensure that sensors and measuring equipment are calibrated;

[0049] Start the test program through the system interface or automated script, and the test program will guide the lifting equipment to operate according to the set test process;

[0050] The operator moves the simulated molten iron load from position A to position B using the lifting equipment to simulate the actual loading process;

[0051] Collect measurement data during the test, analyze the data, and calculate errors and deviations in the test;

[0052] Compare the test results with the data before correction to evaluate the effectiveness of the corrective measures.

[0053] The simulated molten iron load step of the preparation test ensures that the test conditions are close to the actual operating environment, thereby improving the accuracy of the verification of the corrective measures; the step of configuring the test environment to simulate the actual molten iron loading conditions ensures that the sensors and measuring equipment are calibrated, and the simulation of the actual loading conditions helps to verify the performance of the system in the actual production environment; the step of starting the test procedure standardizes the test process, ensures that the tests are performed according to the same standards, and reduces the impact of human errors; the action of operating the simulated molten iron load movement simulates the actual molten iron loading process; collecting and analyzing test data is a direct way to evaluate whether the correction effect meets the expected standards; the step of evaluating the effectiveness of the corrective measures is the key to verifying the success of the corrective measures.

[0054] Preferably, in said S6, the algorithm formula in the automated test program implementation step includes standard deviation, mean square error, and determination coefficient;

[0055] The standard deviation formula: Among them, σ represents the standard deviation of the measurement value, which is used to evaluate the degree of fluctuation of the measurement results;

[0056] The mean square error formula: Among them, MSE represents mean square error;

[0057] The coefficient of determination formula: Here, R represents the coefficient of determination.

[0058] Preferably, in S8, the implementation steps of predictive maintenance are:

[0059] Continuously collect system operation data to ensure the integrity and accuracy of the data for effective analysis;

[0060] Analyze the collected data through statistical analysis and machine learning algorithms to identify failure trends;

[0061] Establish prediction models to estimate the service life or failure time of equipment, and predict equipment failure points through algorithms such as regression analysis, time series analysis, and survival analysis;

[0062] Based on the prediction results, develop maintenance plans and strategies to reduce downtime;

[0063] Utilize the maintenance management system to automatically schedule maintenance tasks and arrange maintenance for critical equipment based on the importance and maintenance urgency of the equipment.

[0064] Preferably, the implementation step of S8 predictive maintenance involves Cobbsmeyer test and neural network model;

[0065] The Kobbsmeier test: Where S(t) is the estimated probability that the equipment has not failed at time t, and d i is at time t i The number of failed devices, n i is at time t i The number of devices currently running;

[0066] The neural network model: y = f(W T x+b), where x is the input vector, W is the weight matrix, b is the bias vector, and f is the activation function.

[0067] The present invention provides an empty ladle correction method for a steelmaking folding tank molten iron metering system. It has the following beneficial effects:

[0068] 1. The present invention reduces human operation errors and measurement errors through the automation function and sensors of the system, ensures the accuracy and repeatability of data, which is crucial to meeting strict quality control standards and reducing waste in the production process. Automated measurement and data processing reduces the need for human intervention and speeds up the correction process to shorten the preparation time for production and improve the operating efficiency of the production line.

[0069] 2. The present invention allows the system to predict and schedule maintenance before a failure occurs through predictive maintenance and self-diagnosis functions, thereby reducing the time and frequency of unexpected downtime. Predictive maintenance can significantly reduce operating costs and increase the service life of equipment. At the same time, environmental monitoring and adaptive correction algorithms enable the system to adjust correction parameters in real time to adapt to changes in the production environment, thereby enhancing the stability and reliability of the system.

[0070] 3. The present invention ensures the instant and accurate recording of data and reduces the risk of data loss or tampering by automating data collection and uploading. In addition, the system's operation log audit function improves overall data transparency and traceability, while automated operations reduce direct interaction between personnel and heavy machinery, thereby reducing the risk of accidents and injuries in the workplace. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Figure 1 The figure is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0072] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0073] The present invention is described in detail below in conjunction with the accompanying drawings:

[0074] Embodiment 1:

[0075] Please refer to the attached Figure 1 The embodiment of the present invention provides an empty ladle correction method for a steelmaking folding tank molten iron metering system, comprising the following steps:

[0076] S1. Initialization system self-check: Automatic and comprehensive self-check is performed when the system is started, including hardware, software, sensor calibration, communication and safety checks to ensure trouble-free system startup;

[0077] S2, operator-assisted empty bag lifting: the operator manually operates the automated lifting equipment to lift the empty bag and uses the sensor integrated system to measure the weight. During the measurement process, the sensor collects data at a higher frequency.

[0078] S3, data processing and correction: the collected data is transmitted to the data processing module, the actual weight of the empty package is calculated by statistical analysis software, and compared with historical data, and the correction parameters are dynamically adjusted using advanced algorithms;

[0079] S4. Simulate actual operation: simulate the molten iron loading process without adding actual molten iron, and test the accuracy and response speed of the system after adjustment;

[0080] S5. Data reporting and analysis: The system automatically uploads measurement and calibration data to the central database, performs data analysis, and predicts future maintenance needs;

[0081] S6, Maintenance and Prevention: Based on the analysis results, the system automatically schedules future maintenance time and notifies the maintenance personnel;

[0082] Summary: Embodiment 1 focuses on operator participation and integrated processing of sensor data, and enhances data accuracy and system responsiveness through high-frequency data acquisition and statistical analysis software.

[0083] Embodiment 2:

[0084] Please refer to the attached Figure 1 The embodiment of the present invention provides an empty ladle correction method for a steelmaking folding tank molten iron metering system, comprising the following steps:

[0085] S1. Automatic startup and self-test: The system automatically starts and performs a comprehensive self-test to check the function and status of each component to ensure that there are no hardware or software faults;

[0086] S2. Automatic empty bag lifting and weight recording: Through the automated lifting system, the empty bag is automatically grabbed and lifted, the sensor automatically records the weight, and the data is displayed in real time in the control system;

[0087] S3, Intelligent Data Analysis: Using the mosaic machine learning model, the system automatically processes the measurement data, calculates the average value, compares it with historical data, and automatically makes corrections;

[0088] S4. Virtual reality testing: Use virtual reality technology to simulate the molten iron loading process to test the accuracy of the calibrated system without using real molten iron, reducing risks and costs;

[0089] S5. Result feedback and predictive maintenance: Test results and system operation data are automatically fed back to the central database, and data analysis is used to predict future failures and maintenance points;

[0090] S6. Automatic maintenance scheduling: The system automatically schedules maintenance tasks based on prediction results, improving maintenance plans and resource allocation;

[0091] Summary: Example 2 reduces manual intervention through fully automated operations, uses virtual reality technology and mosaic machine learning models to improve system efficiency and security, and maintains a production environment with low maintenance costs.

[0092] Embodiment three:

[0093] Please refer to the attached Figure 1 The embodiment of the present invention provides an empty ladle correction method for a steelmaking folding tank molten iron metering system, comprising the following steps:

[0094] S1. System networking startup and self-check: When the system starts, it automatically connects to the network cloud platform for comprehensive remote diagnosis and self-check, including hardware, software and communication integrity check;

[0095] S2, wireless sensing and data collection of empty packages: use wireless sensor networks to sense the location and weight of empty packages, and transmit data to the central processor via wireless networks;

[0096] S3, Data fusion and intelligent analysis: The central processor uses data fusion technology to integrate data from various sensors and automatically analyzes the data through deep learning algorithms to perform error identification and correction suggestions;

[0097] S4, augmented reality assisted simulation: The operator watches the simulated molten iron loading process through augmented reality equipment and receives system feedback in real time to make corrections;

[0098] S5, Intelligent early warning and adjustment: The system automatically adjusts the correction parameters according to the real-time data analysis results, and sends early warning information to the operator through the mobile device;

[0099] S6. Cloud data analysis and reporting: Data is uploaded to the cloud server for long-term analysis, generating performance reports and predictive maintenance recommendations;

[0100] Summary: Example 3 uses cloud computing and wireless sensor technology to enhance the remote processing and real-time analysis capabilities of data, and enhances the operator's interactive experience and correction accuracy through augmented reality technology.

[0101] Embodiment 4:

[0102] Please refer to the attached Figure 1 The embodiment of the present invention provides an empty ladle correction method for a steelmaking folding tank molten iron metering system, comprising the following steps:

[0103] S1. Modular self-check and startup: The system adopts modular design. Each module performs independent self-check at startup and reports the status to the central control system.

[0104] S2. Robotic automatic operation of empty packages: Special robots automatically handle the lifting and placement of empty packages, reducing human intervention;

[0105] S3. Acoustic sensing technology measurement: Use acoustic sensors to measure the weight of empty packages, and determine the weight and volume through changes in sound wave reflection;

[0106] S4, Real-time data correction and optimization: The system receives acoustic sensor data in real time and uses a perfect algorithm to correct errors instantly;

[0107] S5. Continuous improvement of machine learning: The system automatically updates the machine learning model based on the continuously collected data to improve the accuracy of prediction and correction;

[0108] S6. Automatic scheduling of maintenance robots: The maintenance robots automatically schedule maintenance tasks based on system feedback and perform necessary maintenance operations;

[0109] Summary: Example 4 improves operation accuracy and efficiency through robotic automation and acoustic sensing technology.

[0110] Embodiment five:

[0111] Please refer to the attached Figure 1 The embodiment of the present invention provides an empty ladle correction method for a steelmaking folding tank molten iron metering system, comprising the following steps:

[0112] S1. Full connection of IoT devices: All system devices are connected through IoT technology to achieve real-time monitoring of device status and data interaction;

[0113] S2. Blockchain data management: Use blockchain technology to manage measurement data and operation records to ensure data security and immutability;

[0114] S3. Multi-level data analysis and correction: The data were processed through a multi-level analysis model, including primary screening, error analysis, and depth correction;

[0115] S4, fully automatic simulation test: The system uses fully automatic simulation test to verify the calibration results to ensure that each operation meets the preset standards;

[0116] S5. Smart contract automatic execution of maintenance: Using smart contract technology, maintenance and correction tasks are automatically executed according to predetermined rules;

[0117] S6, Visual data report: Generate visual data reports to provide operators with intuitive system status and maintenance suggestions;

[0118] Summary: Example 5 combines the Internet of Things, blockchain and smart contract technologies to provide a highly secure and traceable data management solution, and through multi-level analysis and fully automatic simulation testing, it can achieve precise calibration and efficient system operation and maintenance.

[0119] Comparative experiment 1: Comparison of system self-check and response time;

[0120] Experimental purpose: To compare the self-test and response time before and after the system correction to show the effect of the correction method on improving the system efficiency;

[0121] Experimental setup:

[0122] System status: before and after calibration;

[0123] Test parameters: self-test time, system response time;

[0124] Experimental steps:

[0125] Prerequisites: Ensure that the system is in the same operating environment and initial state before and after calibration;

[0126] System self-check: Start the system self-check and record the time when the self-check is completed;

[0127] System response test: After the self-check is completed, execute standard operation requests, such as starting the empty packet measurement process, and record the time from the operation request to the system starting to respond;

[0128] Data recording: Repeat each test 3 times, record the data, and calculate the average value;

[0129] Comparative analysis: Compare the data before and after correction to evaluate the improvement in time;

[0130] Experimental data table:

[0131] System Status Self-check time(s) System response time(s) Before calibration 45 12 After correction 30 5

[0132] Summary: The experiment shows that the self-check time and response time of the system are significantly reduced after correction. The average self-check time of the system before correction is 45s, which is reduced to 30s after correction. The system response time is reduced from 12s before correction to 5s. This shows that through system correction, the system startup efficiency and operation response speed can be effectively improved, the waiting time can be reduced, and the continuity and efficiency of the production process can be improved. This is especially important for steelmaking operations that require high efficiency, and can significantly improve the operating efficiency of the overall production line.

[0133] Comparative experiment 2: measurement accuracy and repeatability test;

[0134] Experimental purpose: To demonstrate the effect of the correction method in improving data accuracy and stability by comparing the measurement accuracy and repeatability before and after correction;

[0135] Experimental setup:

[0136] System status: before and after calibration;

[0137] Test parameters: measurement accuracy error, measurement repeatability;

[0138] Experimental steps:

[0139] Prepare test materials: Prepare a standard mass of test material, whose weight is known and close to the weight of the empty bag;

[0140] Measurement accuracy test:

[0141] a. Place the test object in the measurement system;

[0142] b. Record the weight measured by the system;

[0143] c. Calculate the percentage error between the measured value and the actual value;

[0144] Repeatability test:

[0145] a. Repeat the measurement of the same test object 10 times;

[0146] b. Record 10 measurements;

[0147] c. Calculate the standard deviation of 10 measurements;

[0148] Data recording and analysis: statistics and comparison of data before and after calibration to evaluate the impact of calibration on measurement accuracy and repeatability;

[0149] Experimental data table:

[0150] System Status Measurement accuracy error (%) Measurement repeatability Before calibration 1.5 0.3 After correction 0.5 0.1

[0151] Summary: After implementing the correction measures, the measurement accuracy and repeatability were significantly improved. The measurement error before correction was 1.5%, which was reduced to 0.5% after correction. The standard deviation of the measurement was reduced from 0.3 to 0.1, showing higher repeatability. This shows that the correction method can accurately adjust the measurement system, reduce errors, and enhance the reliability of the data.

[0152] Comparative experiment 3: predictive maintenance and system stability test;

[0153] Experimental purpose: To evaluate the improvement effect of the correction method on the system predictive maintenance, especially in terms of equipment stability and maintenance frequency;

[0154] Experimental setup:

[0155] System status: before and after calibration;

[0156] Test parameters: system failure frequency, average maintenance interval days;

[0157] Experimental steps:

[0158] Monitoring system operation: During normal system operation, continuously monitor and record system failure events;

[0159] Record maintenance frequency: Count the number of times the system is maintained within a specified time period, and record the number of days between maintenance times;

[0160] Fault analysis: Analyze the fault types and frequencies before and after correction to determine whether the corrective measures reduce the occurrence of faults;

[0161] Predictive maintenance testing: Use the system's predictive maintenance function to monitor and record the accuracy and effectiveness of the system's early warning.

[0162] Data collation and comparison: Compare system stability and maintenance requirements before and after correction, and evaluate the long-term benefits of correction measures;

[0163] Experimental data table:

[0164] System Status System failure frequency (times / year) Average maintenance interval (days) Before calibration 10 90 After correction 2 180

[0165] Summary: The experimental results show that the failure frequency of the system after correction has dropped significantly, from 10 times per year to 2 times, and the average maintenance interval has been extended from 90 days to 180 days. The significant improvement shows that the correction method enhances the stability of the system and effectively extends the maintenance cycle of the equipment through the predictive maintenance function to reduce maintenance costs and the frequency of unplanned downtime.

[0166] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for correcting an empty ladle in a steelmaking folding tank hot metal metering system, characterized in that: The following steps are involved: S1. When the system is started, it will automatically conduct a comprehensive self-check. When the self-check is completed, an empty package of the same model and specification as that in production will be taken from the system record; S2. The operator lifts the empty bag through the automated lifting equipment, and the sensor records the weight of the empty bag and performs multiple measurements continuously; S3. The system automatically calculates the average value of multiple measurement results and compares it with historical data; S4, the system automatically uploads the measurement data to the central database; S5. The system uses machine learning algorithms to analyze the sources of errors in the measurement data, make correction suggestions, and correct the parameters according to the algorithm formula; S6. Execute the automated test program to simulate the molten iron loading process and verify the accuracy after correction; S7. The system automatically performs empty package correction regularly without manual intervention; S8. The system uses the collected operation data for predictive maintenance, automatically schedules maintenance tasks, and reduces downtime; S9. The system has monitoring functions and can automatically record operations and modifications for auditing and tracing.

2. The method for correcting an empty ladle of a molten iron metering system for a steelmaking folding tank according to claim 1, characterized in that: In S1, the implementation steps of the system self-check are: Hardware check: The system checks the connection status and functionality of the connected hardware devices to ensure there is no physical damage or connection errors; Software verification: The system checks that its internal software components are intact and that software updates and patches have been installed; Sensor calibration: Check the calibration status of the sensor to ensure the accuracy of sensor data; Communication test: The system performs internal and external communication tests to ensure that data can be transmitted between system components; Performance test: System operation performance test, simulating the operation process of hot metal metering in steelmaking folding tanks, and checking whether the processing speed and response time meet the expected standards; Security check: Perform system security checks to ensure that the system is protected from unauthorized access and security threats; Backup status verification: Check the backup status of system data to ensure that the backup data can be restored in time.

3. The method for correcting an empty ladle of a molten iron metering system for a steelmaking folding tank according to claim 1, characterized in that: In S3, the calculation formula of the average value is: Among them, x i represents the empty bag weight measured for the i-th time, and n is the number of measurements.

4. The method for correcting an empty ladle in a molten iron metering system for a steelmaking folding tank according to claim 1, characterized in that: In S4, the central database includes a database management system, a data storage module, a data model module, an access control module, and an interface; the database management system is responsible for the storage, query, update, and management of data; the data storage module is used to store data; the data model module is used to define the structure of data; the access control module is used to manage the authority to access the database; the interface is used to provide an interface for interacting with the system or application, allowing remote query and management.

5. The method for correcting an empty ladle of a molten iron metering system for a steelmaking folding tank according to claim 1, characterized in that: In S5, the implementation steps of analyzing the error sources of the measurement data and proposing correction suggestions through a machine learning algorithm are as follows: Collect historical measurement data; Mark the relevant information of environmental conditions and equipment status for each measurement; Extract features of historical data related to measurement errors; Machine learning algorithms based on data characteristics are used to model and analyze sources of measurement errors; Train machine learning models using historical data to predict the relationship between measurement error and various features; Analyze the results of the model to determine the degree of influence of each feature on the measurement error and make correction suggestions based on the analysis results; Adjust system parameters according to the correction suggestions and determine the specific implementation steps of the correction parameters; Run the calibrated system and collect new measurement data. At the same time, regularly monitor system performance to ensure that the calibration effect continues to be stable.

6. The method for correcting an empty ladle in a molten iron metering system for a steelmaking folding tank according to claim 5, characterized in that: In S5, the machine learning algorithm includes linear regression, logistic regression, and support vector machine; The linear regression: y = β0 + β1x1 + β2x2 + ... + β n x n +∈, where y is the predicted value, β0,β1,...,β n are the model parameters, x1,x2,...,x n is the characteristic variable, ∈ is the error term; The logistic regression: Among them, p(y=1|x) is the probability of output being 1 under the condition of input x, β0,β1,...,β n are model parameters; The support vector machine: subject toys i (w·x i -b)≥1-ξ i ,fori=1,2,...,n,ξ i ≥0,fori=1,2,...,n, where w is the weight vector, b is the bias, ξ i is the slack variable and C is the penalty parameter.

7. The method for correcting an empty ladle in a molten iron metering system for a steelmaking folding tank according to claim 1, characterized in that: In S6, the implementation steps of executing the automated testing program are: Prepare simulated hot metal loads for testing and, if practicable, use actual hot metal or equivalent test material; Configure the test environment to simulate actual hot metal loading conditions and ensure that sensors and measuring equipment are calibrated; Start the test program through the system interface or automated script, and the test program will guide the lifting equipment to operate according to the set test process; The operator moves the simulated molten iron load from position A to position B using the lifting equipment to simulate the actual loading process; Collect measurement data during the test, analyze the data, and calculate errors and deviations in the test; Compare the test results with the data before correction to evaluate the effectiveness of the corrective measures.

8. The method for correcting an empty ladle in a molten iron metering system for a steelmaking folding tank according to claim 7, characterized in that: In said S6, the algorithm formula in the automated test program implementation step includes standard deviation, mean square error, and determination coefficient; The standard deviation formula: Among them, σ represents the standard deviation of the measurement value, which is used to evaluate the degree of fluctuation of the measurement result; The mean square error formula: Among them, MSE represents mean square error; The coefficient of determination formula: Here, R represents the coefficient of determination.

9. The method for correcting an empty ladle in a molten iron metering system for a steelmaking folding tank according to claim 1, characterized in that: In S8, the implementation steps of predictive maintenance are: Continuously collect system operation data to ensure the integrity and accuracy of the data for effective analysis; Analyze the collected data through statistical analysis and machine learning algorithms to identify failure trends; Establish prediction models to estimate the service life or failure time of equipment, and predict equipment failure points through algorithms such as regression analysis, time series analysis, and survival analysis; Based on the prediction results, develop maintenance plans and strategies to reduce downtime; Utilize the maintenance management system to automatically schedule maintenance tasks and arrange maintenance for critical equipment based on the importance and maintenance urgency of the equipment.

10. The method for correcting an empty ladle in a molten iron metering system for a steelmaking folding tank according to claim 9, characterized in that: The implementation steps of the S8 predictive maintenance involve the Cobbsmeyer test and the neural network model; The Kobbsmeier test: Where S(t) is the estimated probability that the equipment has not failed at time t, and d i is at time t i The number of failed devices, n i is at time t i The number of devices currently running; The neural network model: y = f(W T x+b), where x is the input vector, W is the weight matrix, b is the bias vector, and f is the activation function.

Images