Pre-warning method for earnings and loss of iron in front of furnace

Abstract

The invention discloses a pre-warning method for furnace-front iron loss and profit. Comprising the following steps of: acquiring basic data, namely acquiring furnace top charging related data at a second level, acquiring molten iron weighing data at a minute level, acquiring multi-source data, including blast furnace related temperature and other data and fusing the basic data, arranging a redundant channel, processing the acquired data and judging a furnace top charging signal, judging a material type signal by using fuzzy logic and the like, and calculating an iron profit and loss amount; comprising the steps of calculating the furnace top charging minute theoretical yield and the like, updating the accumulated iron profit and loss amount, pre-warning the furnace front iron profit and loss amount and the like. The method has many advantages, can monitor the iron profit and loss in real time, and improves the timeliness and accuracy of production management; multi-source data acquisition enables furnace condition monitoring to be more comprehensive, and redundant channels guarantee data transmission stability. And fuzzy logic is used for judging material type signals to improve the iron loss and profit calculation accuracy, and an early warning mechanism is further arranged to avoid production risks.

Description

Technical Field

[0001] The present invention relates to the application field of blast furnace ironmaking, and in particular to a furnace front iron quantity profit or loss early warning method. Background Art

[0002] Blast furnace ironmaking is a core process in the steelmaking process. Raw materials (such as ore and coke) are added to the blast furnace in specific proportions and sequences, undergoing complex physical and chemical reactions to produce molten iron. The iron production at the blast furnace directly reflects the stability of the blast furnace production process, the rationality of the raw material ratio, and the precision of operational control.

[0003] Controlling and optimizing common blast furnace production processes is crucial for improving output, quality, and economic benefits. Traditional blast furnace production management relies on manual experience and lacks real-time data support, leading to untimely production adjustments and impacting production efficiency and product quality. Furthermore, existing blast furnace production management typically uses regular statistics of feed and iron output for profit and loss analysis. However, this method introduces time delays, preventing real-time monitoring and early warning, and failing to meet the operational requirements of blast furnace ironmaking. Therefore, a pre-furnace iron production early warning method for profit and loss was proposed. Summary of the Invention

[0004] The present invention provides the following technical solution: a furnace front iron quantity early warning method, comprising the following steps: S1 basic data collection stage: First, the top charging weight, material type signal, and top charging signal in the blast furnace's first-level PLC are captured at a frequency of seconds. At the same time, the minute flow rate and real-time weight of the molten iron online weighing in front of the furnace are captured at a frequency of minutes, thereby obtaining the real-time material type and weight of the blast furnace top charging and the real-time iron tapping flow rate of the molten iron online weighing in front of the furnace; S11 multi-source data acquisition: After the data collection in step S1 is completed, multi-source data related to the blast furnace condition is collected. The multi-source data includes temperature data at different locations in the blast furnace, furnace wall pressure data, and ambient humidity and atmospheric pressure data around the blast furnace. The multi-source data is then fused with the basic data captured in step S1, and a redundant channel for data transmission is established during the data collection process. S2 data collection and processing stage: Real-time judgment of the furnace top charging signal captured in step S1, and the use of a fuzzy logic system to judge the furnace top material type signal, while using a dynamic threshold adjustment mechanism to process the collected minute molten iron flow rate; S3 profit and loss iron quantity calculation stage: Based on the data obtained in step S1 and processed in step S2, the theoretical output of the top charging minute, the profit and loss of iron in front of the furnace minute and the molten iron flow rate status are calculated, and the cumulative profit and loss of iron is updated at the same time; S4 furnace profit and loss iron quantity early warning stage: An early warning is issued based on the result calculated in step S3.

[0005] Preferably, in step S1, the specific method of capturing the top charging weight, material type signal and top charging signal in the blast furnace first-level PLC at a frequency of seconds is to directly obtain the corresponding data from the storage area and data interface corresponding to the blast furnace first-level PLC.

[0006] Preferably, in the step S2, when judging the furnace top feeding signal in real time, the judgment is performed through a preset signal detection program, and the preset signal detection program is internally provided with functional modules for detecting signal strength, signal stability and signal interference. And when judging the furnace top material type signal in step S2, the obtained material type signal is determined by comparing it with the preset ore and coke identifications. At the same time, when the fuzzy logic system is used to judge the furnace top material type signal, a fuzzy logic knowledge base containing detailed material characteristic parameters and corresponding fuzzy rules is synchronously constructed.

[0007] Preferably, in step S3, the theoretical output per minute of top charging is calculated based on the weight of top charging and the difference in charging time.

[0008] Preferably, in step S3, the minute molten iron flow rate is compared with a dynamic threshold range to determine whether the minute molten iron flow rate is a normal molten iron flow rate.

[0009] Preferably, in step S3, when calculating the profit and loss iron amount in front of the furnace in this minute, the calculation formula is: the profit and loss iron amount in front of the furnace in this minute = the molten iron flow rate in minutes - the theoretical output of the furnace top charging in minutes. Finally, when updating the cumulative profit and loss iron amount, the calculation is performed according to the formula: the profit and loss iron amount in front of the furnace = the profit and loss iron amount in front of the last furnace + the profit and loss iron amount in front of the furnace in this minute.

[0010] Preferably, in step S4, first, the warning value of the cumulative profit and loss iron amount is determined based on no less than five production tests, statistical analysis results and multi-source data, and then it is judged in real time whether the profit and loss iron amount in front of the furnace calculated in step S3 is greater than the warning value of the cumulative profit and loss iron amount. If it is greater, it is further judged whether there is a prompt that the profit and loss iron amount in front of the furnace exceeds the warning value within the previous 20 minutes. If not, it is prompted that the cumulative profit and loss iron amount in front of the furnace exceeds the warning value. If so, this round of judgment ends; if the profit and loss iron amount in front of the furnace is not greater than the warning value of the cumulative profit and loss iron amount, this round of judgment ends.

[0011] Preferably, in the multi-source data collection process of step S11, temperature sensors are used to collect temperature data at different positions in the blast furnace. The temperature sensors are evenly distributed at different positions inside the blast furnace, and each sensor is calibrated regularly.

[0012] Preferably, when establishing a redundant channel for data transmission in step S11, the main channel and the backup channel of the redundant channel should use different transmission media, the main channel uses optical fiber transmission, and the backup channel uses wireless transmission. At the same time, an intelligent monitoring mechanism for channel switching is set inside the redundant channel. When the data transmission of the main channel exceeds the packet loss rate, exceeds the delay, and the signal is interrupted, it automatically switches to the backup channel.

[0013] Preferably, when the step S3 updates the cumulative profit and loss iron volume, a data verification mechanism is set before each update. The data verification mechanism will first check whether the data of the profit and loss iron volume in front of the furnace in one minute is within the range. If the calculated profit and loss iron volume in front of the furnace in one minute exceeds the average value of historical data, it is considered that the data is abnormal, and for abnormal data, interpolation method is used for processing.

[0014] In summary, compared with the prior art, the present invention provides a furnace front iron quantity early warning method with the following beneficial effects: 1. The present invention realizes real-time monitoring of the surplus and deficit iron quantity in the blast furnace production process through real-time data collection and processing, thereby improving the timeliness and accuracy of production management. Moreover, the dynamic surplus and deficit iron quantity calculation method can more accurately reflect the blast furnace production status, which helps to optimize the production process. In addition, the real-time early warning mechanism is set up to promptly remind the operator when the surplus and deficit iron quantity reaches a critical value, effectively avoiding potential production risks and improving production safety and efficiency. 2. The present invention integrates data such as temperature, furnace wall pressure, ambient humidity and atmospheric pressure at different positions in the blast furnace with basic data through multi-source data acquisition. This comprehensive data acquisition method makes the monitoring of the blast furnace condition more comprehensive, and the profit and loss iron quantity can be predicted more accurately through comprehensive analysis. The redundant channels for data transmission are added, so that during the data acquisition process, even if the main channel has problems such as packet loss, delay or signal interruption, the backup channel can be switched in time to ensure uninterrupted data transmission, thereby improving the stability of the calculation and early warning process of the profit and loss iron quantity in front of the furnace; 3. The present invention uses a fuzzy logic system to judge the top material signal during the data collection and processing stage. Compared with the traditional simple comparison judgment method, the fuzzy logic system can comprehensively consider the multiple characteristics of the material, construct a knowledge base containing detailed material characteristic parameters and corresponding fuzzy rules, and thus more accurately judge the material signal. This helps to more accurately calculate key data such as the theoretical output of the top material in one minute, thereby improving the accuracy of the calculation of the profit and loss of iron in the furnace. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a flow chart of the furnace front profit and loss iron quantity early warning method of the present invention. DETAILED DESCRIPTION

[0016] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0017] See also Figure 1 , the present invention provides a technical solution, a furnace front iron profit and loss early warning method, comprising the following steps; S1 basic data collection stage: First, the top charging weight, material type signal, and top charging signal in the blast furnace's first-level PLC are captured at a frequency of seconds. The specific method is to directly obtain the corresponding data from the storage area and data interface corresponding to the blast furnace's first-level PLC. At the same time, the minute flow rate and real-time weight of the molten iron online weighing in front of the furnace are captured at a frequency of minutes, thereby obtaining the real-time material type and weight of the blast furnace top charging and the real-time iron tapping flow rate of the molten iron online weighing in front of the furnace; S11 multi-source data acquisition: After the data collection in step S1 is completed, multi-source data related to the blast furnace condition is collected. The multi-source data includes temperature data at different locations in the blast furnace, furnace wall pressure data, and ambient humidity and atmospheric pressure data around the blast furnace. Temperature data at different locations in the blast furnace are collected using temperature sensors. The temperature sensors are evenly distributed at different locations inside the blast furnace, and each sensor is regularly calibrated. The multi-source data is then fused with the basic data captured in step S1. The specific method for data fusion is as follows: First, the basic data captured in step S1 (furnace top charging weight, material type signal, furnace top charging signal, minute flow rate and real-time weight of molten iron online weighing in front of the furnace) and multi-source data (temperature data at different locations in the blast furnace, furnace wall pressure data, ambient humidity and atmospheric pressure data around the blast furnace) are checked for data format. The data in different formats are then converted to a unified format, for example, all data is converted to digital format, and the unit and accuracy requirements for each data are determined. For example, temperature data is unified into degrees Celsius, and pressure data is unified into Pascals. Check for outliers in basic data and multi-source data. For basic data, if the weight of the furnace top charge suddenly reaches a maximum or minimum value that does not conform to production logic, it will be marked as an outlier. For multi-source data, if the temperature data exceeds the normal operating temperature range of the blast furnace, it will be considered an outlier. For correctable outliers, interpolation correction can be performed based on adjacent data or historical data; for serious outliers that cannot be corrected, the data point can be discarded. According to the physical and chemical principles of the blast furnace production process, the correlation between basic data and multi-source data is determined. For example, changes in the temperature inside the blast furnace may affect the reaction rate of the top charging, and thus affect the weight of the top charging and the molten iron output, etc., and appropriate data fusion algorithms are used, such as weighted average method, Kalman filter method, etc. If the weighted average method is used, different weights are assigned according to the importance of each data to the profit and loss of iron in front of the furnace. For example, the weight of the top charging may be assigned a higher weight because it is directly related to the output of molten iron; while the ambient humidity may be assigned a relatively low weight. The cleaned and correlated basic data and multi-source data are fused according to the selected fusion algorithm to obtain a set of fused data that comprehensively reflects the blast furnace condition and the profit and loss of iron in front of the furnace, which is used for subsequent calculations and analysis; During the data collection process, a redundant channel for data transmission is established. The main channel and the backup channel of the redundant channel should use different transmission media. The main channel uses optical fiber transmission, and the backup channel uses wireless transmission. At the same time, an intelligent monitoring mechanism for channel switching is set inside the redundant channel. When the data transmission of the main channel exceeds the packet loss rate, exceeds the delay, or is interrupted, it automatically switches to the backup channel. The specific implementation process of the above method is as follows: First, set monitoring parameters to determine the thresholds for packet loss rate, latency, and signal interruption. For packet loss rate, set a reasonable upper limit based on the reliability requirements of data transmission and the characteristics of the network protocol. For example, set a packet loss rate exceeding 5% as an abnormality. For latency, consider the real-time requirements of blast furnace data and set a maximum allowable delay time, such as 100 milliseconds. For signal interruption, define a signal interruption as a continuous period (e.g., 5 seconds) without receiving a valid data signal. Data monitoring module initialization: A dedicated data monitoring module is set up within the redundant channel. This module is responsible for real-time monitoring of data transmission on the primary channel. It starts when data transmission on the primary channel begins and runs continuously to ensure that anomalies in data transmission can be detected in a timely manner. Packet loss rate monitoring: During data transmission on the primary channel, the data monitoring module counts the number of lost packets within each data transmission cycle (e.g., per second). The packet loss rate is calculated by comparing the number of packets sent with the number of packets actually received. If the calculated packet loss rate exceeds a pre-set threshold (e.g., 5%), the initial judgment process for channel switching is triggered. Delay monitoring: At the same time, the data monitoring module measures the time interval from the sending to the receiving of each data packet to determine the delay of data transmission. When the delay time exceeds the set maximum allowable delay time (such as 100 milliseconds), the preliminary judgment process of channel switching is also triggered; Signal interruption monitoring: The data monitoring module continuously detects whether there is a signal input in the main channel. If no valid signal input is detected within a continuous period of time (such as 5 seconds), it is determined to be a signal interruption, and the preliminary judgment process of channel switching is also triggered; Initial channel switching judgment: When any of the packet loss rate, latency, or signal interruption triggers the initial judgment process, the data monitoring module will further check whether there is a temporary network fluctuation or a recoverable fault. For example, it may monitor the relevant parameters again within a short period of time (such as 1-2 seconds). If the relevant parameters return to normal, channel switching will not be performed. If the abnormality persists, channel switching is determined to be necessary. Channel switching execution: Once a channel switch is determined, the data monitoring module sends a switching instruction to the control unit of the redundant channel. Upon receiving the instruction, the control unit switches the data transmission path from the primary channel (fiber transmission) to the backup channel (wireless transmission). During the switching process, data continuity must be ensured to avoid data loss. For example, caching technology can be used to cache a certain amount of untransmitted data before the switch, and then prioritize the transmission of this cached data after the switch. S2 data collection and processing stage: Real-time judgment of the furnace top charging signal captured in step S1, and the use of a fuzzy logic system to judge the furnace top material type signal, while using a dynamic threshold adjustment mechanism to process the collected minute molten iron flow rate; The process of using the fuzzy logic system to judge the furnace top material type signal is as follows: Construct a fuzzy logic knowledge base: Determine detailed material characteristic parameters related to the furnace top material. These parameters may include material density, particle size, humidity, etc. For example, for ore materials, their density range may be within a certain interval, and their particle size distribution may vary. Based on production experience and expert knowledge, establish corresponding fuzzy rules for these material characteristic parameters. For example, if the material's density is within a certain range, its particle size is within a certain interval, and its humidity is below a certain value, then it can be determined to be a certain type of ore material. These fuzzy rules are summarized to construct a fuzzy logic knowledge base; Fuzzify input data: Obtain relevant data from the furnace top material signal, such as possible measurements related to material properties. Convert this precise input data into fuzzy sets. For example, for the parameter density, if the actual measured value is x grams per cubic centimeter, determine the membership of the fuzzy set to which the measured value belongs based on pre-defined fuzzy set definitions (such as low density, medium density, and high density). Fuzzy reasoning: Based on the fuzzy rules in the fuzzy logic knowledge base, reasoning is performed on the fuzzified input data. For example, if the input density belongs to the medium density fuzzy set, the particle size belongs to the medium particle size fuzzy set, and the humidity belongs to the low humidity fuzzy set, the possible material type conclusion can be drawn through fuzzy rule reasoning. This process involves fuzzy logic operations such as min and max operations. Defuzzification: Convert the fuzzy results obtained by fuzzy reasoning into precise material type judgments. For example, through defuzzification methods such as the centroid method and the maximum membership method, the fuzzy material type conclusions can be converted into clear judgments on specific material types such as "ore A" or "coke B"; The process of processing the collected minute molten iron flow rate using the dynamic threshold adjustment mechanism is as follows: Initial threshold setting: Based on the blast furnace's historical production data, analyze the range of the minute molten iron flow rate under normal production conditions. For example, by collecting minute molten iron flow rate data during normal production over a period of time (e.g., one month), determine an initial threshold range, such as a minimum of v1 cubic meter / minute and a maximum of v2 cubic meters / minute. Dynamic monitoring and data collection: During the production process, minute-by-minute molten iron flow rate data is continuously collected. Other data that may be related to molten iron flow rate is also collected, such as top charge weight, furnace temperature, pressure, and other multi-source data. This data will be used to dynamically adjust the threshold; Threshold adjustment decision: Based on the relevant data collected, determine whether the threshold needs to be adjusted. For example, if the weight of the furnace top charging increases, it may cause the molten iron flow rate to increase accordingly. In this case, the upper limit of the threshold may need to be appropriately increased. Threshold adjustment decisions can be made by establishing a data association model or based on empirical rules. If a major change in production conditions is detected, such as replacing the furnace lining material, which may affect the heat transfer in the furnace and thus the molten iron flow rate, or adopting a new charging process, the threshold also needs to be re-evaluated and adjusted; Threshold Update and Flow Rate Judgment: Based on the threshold adjustment decision results, the threshold range for the minute molten iron flow rate is updated. The collected minute molten iron flow rate is then compared with the updated threshold range to determine whether the molten iron flow rate is within the normal range. If the flow rate is within the threshold range, the molten iron flow rate is considered normal; if the flow rate exceeds the threshold range, it may indicate an abnormality in the production process, requiring further analysis or appropriate measures. When judging the furnace top charging signal in real time, the judgment is made through a preset signal detection program, which is internally provided with a functional module for detecting signal strength, signal stability and signal interference. When judging the furnace top material type signal in step S2, the obtained material type signal is determined by comparing it with the preset identification of ore and coke; At the same time, when the fuzzy logic system is used to judge the furnace top material type signal, a fuzzy logic knowledge base containing detailed material characteristic parameters and corresponding fuzzy rules is simultaneously constructed. The specific process of the above method is as follows; First, determine the material characteristic parameters: conduct a detailed analysis of the possible material types (such as ore, coke, etc.) on the blast furnace top to determine the various factors that affect the material type judgment. These factors include physical properties, such as density (ρ), particle size (d), shape, etc.; chemical properties, such as chemical composition (for example, the iron content Fe% in ore, the fixed carbon content C% in coke, etc.); and other related characteristics, such as humidity (H), etc., and collect data on these material characteristic parameters from historical production data, laboratory analysis results, and online monitoring data during the production process. For example, collect density measurements, particle size distribution data, and chemical composition analysis reports of different batches of ore, organize the collected data, remove outliers, and classify them according to material type. For example, all relevant characteristic parameter data about ore materials are grouped together, and data about coke materials are grouped together. Define fuzzy sets: For each material characteristic parameter, determine the range of the fuzzy set based on its data distribution and actual production requirements. Taking density as an example, if the density of the ore ranges from 2.5 to 5.0 g / cm³, you can define a "low density" fuzzy set as [2.5, 3.5) g / cm³, a "medium density" fuzzy set as [3.5, 4.5) g / cm³, and a "high density" fuzzy set as [4.5, 5.0) g / cm³. For particle size, you can determine the corresponding fuzzy set range based on common production classifications such as "small particle size," "medium particle size," and "large particle size." For example, the "small particle size" fuzzy set is [0, 5) mm, the "medium particle size" fuzzy set is [5, 15) mm, and the "large particle size" fuzzy set is [15, +∞) mm. Establish fuzzy rules: Based on the knowledge of judging the type of blast furnace top material, establish fuzzy rules. For example, if the density of the ore is "medium density", the particle size is "medium particle size", the iron content is "high" and the humidity is "low", then it is judged to be a high-quality ore material, taking into account the relationship between different material characteristic parameters. For example, there may be a certain correlation between density and particle size. Materials with smaller particle size may have higher density. This relationship should be reflected when establishing fuzzy rules. The fuzzy rules are expressed in the form of "IF-THEN". For example: IF (density is medium density) AND (particle size is medium particle size) AND (iron content is high) AND (humidity is low) THEN (material type is high-quality ore). According to this form, a series of fuzzy rules covering various possible situations are established to form a complete rule base; Construct a fuzzy logic knowledge base: Integrate the fuzzy sets of all defined material characteristic parameters and the established fuzzy rules to form a fuzzy logic knowledge base containing detailed material characteristic parameters and corresponding fuzzy rules. This knowledge base can be stored in the form of a database, which is convenient for querying and calling when using the fuzzy logic system to judge the furnace top material type signal. Use the furnace top material type signal data in the historical production data to verify the constructed fuzzy logic knowledge base. Input the actual material type signal data into the fuzzy logic system based on the knowledge base to see whether the judgment result is consistent with the actual material type, and optimize the knowledge base according to the verification result. If it is found that some fuzzy rules are inaccurate or the definition of the fuzzy set is unreasonable, adjust them and then verify again until a satisfactory judgment accuracy rate is achieved; S3 profit and loss iron quantity calculation stage: Based on the data obtained in step S1 and processed in step S2, the theoretical output of the top charging minute, the profit and loss of iron in front of the furnace minute and the molten iron flow rate status are calculated, and the cumulative profit and loss of iron is updated at the same time; The theoretical output per minute of top charging is calculated based on the weight of top charging and the difference in charging time. The specific calculation process is as follows: First, data acquisition is performed: the furnace top charging weight data is obtained from the S1 basic data acquisition stage. In this stage, the furnace top charging weight data is captured from the storage area and data interface corresponding to the blast furnace first-level PLC at a frequency of seconds. Since the data is collected at the second level, these second-level data need to be integrated and processed when calculating the theoretical output of the furnace top charging in minutes. For example, the summation or weighted average method (determined according to the actual production situation) can be used to convert the second-level furnace top charging weight data into minute-level data, determine the time interval for calculating the output, and obtain the start time and end time of the time interval. These two time points can be obtained from the timestamp in the data acquisition system, and the charging time difference is calculated, that is, the end time minus the start time, to obtain the time difference in minutes. For example, if the start time is the 0th second of the 1st minute and the end time is the 0th second of the 2nd minute, then the charging time difference is 1 minute; Calculate the theoretical output per minute of top charging: Use an appropriate calculation method based on the physical and chemical principles of the production process. Since the calculation is based on the weight of the top charging and the difference in charging time, a simple division method is used here to divide the acquired and processed top charging weight (based on minute-level data) by the charging time difference (in minutes) to obtain the theoretical output per minute of top charging; The method of comparing the minute molten iron flow rate with the dynamic threshold range is used to determine whether the minute molten iron flow rate is a normal molten iron flow rate; When calculating the profit or loss of iron in front of the furnace in one minute, the calculation formula is: the profit or loss of iron in front of the furnace in one minute = the molten iron flow rate in one minute - the theoretical output of the furnace top charging in one minute; When updating the cumulative profit and loss iron volume, the formula is used: profit and loss iron volume before the furnace = profit and loss iron volume before the previous furnace + profit and loss iron volume before the current furnace minute. A data verification mechanism is set before each update. The data verification mechanism will first check whether the data of the profit and loss iron volume before the current furnace minute is within the range. If the calculated profit and loss iron volume before the current furnace minute exceeds the average value of historical data, it is considered that the data is abnormal. For abnormal data, the interpolation method is used for processing. The specific process of the above method is as follows; First, calculate the average of historical data: Collect data on the minute profit and loss of iron at the furnace from historical production data. This data should cover a sufficiently long production cycle to ensure that the data is representative. For example, collect data on the minute profit and loss of iron at the furnace for the past month or quarter and calculate the average of the collected historical minute profit and loss of iron at the furnace. Checking the profit and loss iron quantity data of this furnace: After calculating the average profit and loss iron quantity of this furnace every time, start the data verification mechanism, that is, compare the average profit and loss iron quantity of this furnace with the predetermined range. When it is determined that the profit and loss iron quantity data of this furnace is abnormal, it is necessary to use the interpolation method to process it. First, determine the adjacent data points for interpolation. According to the time sequence of the data, find the normal data points before and after the abnormal data, and select the appropriate interpolation method according to the characteristics of the data. Common interpolation methods include linear interpolation, quadratic interpolation, etc. S4 furnace profit and loss iron quantity early warning stage: An early warning is issued based on the result calculated in step S3. First, the early warning value of the cumulative profit and loss iron amount is determined based on no less than five production tests, statistical analysis results and multi-source data. Then, it is judged in real time whether the profit and loss iron amount before the furnace calculated in step S3 is greater than the early warning value of the cumulative profit and loss iron amount. If it is greater, it is further judged whether there is a prompt that the profit and loss iron amount before the furnace exceeds the early warning value within the previous 20 minutes. If not, it is prompted that the cumulative profit and loss iron amount before the furnace exceeds the early warning value. If so, this round of judgment ends; if the profit and loss iron amount before the furnace is not greater than the early warning value of the cumulative profit and loss iron amount, this round of judgment ends.

[0018] Through real-time data collection and processing, this solution realizes real-time monitoring of the surplus and deficit iron volume during the blast furnace production process, improving the timeliness and accuracy of production management. The dynamic surplus and deficit iron volume calculation method can more accurately reflect the blast furnace production status and help optimize the production process. In addition, through the set real-time early warning mechanism, it can promptly remind operators when the surplus and deficit iron volume reaches the critical value, effectively avoiding potential production risks and improving production safety and efficiency.

[0019] Secondly, this solution integrates data such as temperature, furnace wall pressure, ambient humidity and atmospheric pressure at different locations in the blast furnace with basic data through multi-source data collection. This comprehensive data collection method makes the monitoring of blast furnace conditions more comprehensive, and through comprehensive analysis, the profit and loss of iron can be predicted more accurately. The added redundant data transmission channel ensures that during the data collection process, even if the main channel has problems such as packet loss, delay or signal interruption, the backup channel can be switched in time to ensure uninterrupted data transmission, thereby improving the stability of the calculation and early warning process of the profit and loss of iron in front of the furnace.

[0020] Finally, during the data collection and processing phase, this solution uses a fuzzy logic system to determine the top charge type signal. Compared to traditional simple comparison judgment methods, the fuzzy logic system comprehensively considers multiple material characteristics, constructing a knowledge base containing detailed material characteristic parameters and corresponding fuzzy rules, thereby more accurately determining the charge type signal. This helps to more accurately calculate key data such as the theoretical output per minute of top charge addition, thereby improving the accuracy of calculations of profit and loss iron production at the furnace.

[0021] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0022] While 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 these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A furnace front iron quantity early warning method, characterized in that: The following steps are involved: S1 basic data collection stage: First, the top charging weight, material type signal, and top charging signal in the blast furnace's first-level PLC are captured at a frequency of seconds. At the same time, the minute flow rate and real-time weight of the molten iron online weighing in front of the furnace are captured at a frequency of minutes, thereby obtaining the real-time material type and weight of the blast furnace top charging and the real-time iron tapping flow rate of the molten iron online weighing in front of the furnace; S11 multi-source data acquisition: After the data collection in step S1 is completed, multi-source data related to the blast furnace condition is collected. The multi-source data includes temperature data at different locations in the blast furnace, furnace wall pressure data, and ambient humidity and atmospheric pressure data around the blast furnace. The multi-source data is then fused with the basic data captured in step S1, and a redundant channel for data transmission is established during the data collection process. S2 data collection and processing stage: Real-time judgment of the furnace top charging signal captured in step S1, and the use of a fuzzy logic system to judge the furnace top material type signal, while using a dynamic threshold adjustment mechanism to process the collected minute molten iron flow rate; S3 profit and loss iron quantity calculation stage: Based on the data obtained in step S1 and processed in step S2, the theoretical output of the top charging minute, the profit and loss of iron in front of the furnace minute and the molten iron flow rate status are calculated, and the cumulative profit and loss of iron is updated at the same time; S4 furnace profit and loss iron quantity early warning stage: An early warning is issued based on the result calculated in step S3.

2. The method for early warning of iron quantity surplus or deficit in a furnace according to claim 1, characterized in that: In step S1, the specific method of capturing the top charging weight, material type signal and top charging signal in the blast furnace first-level PLC at a frequency of seconds is to directly obtain the corresponding data from the storage area and data interface corresponding to the blast furnace first-level PLC.

3. The method for early warning of iron surplus or deficit in a furnace according to claim 1, characterized in that: In the step S2, when judging the furnace top charging signal in real time, the judgment is performed through a preset signal detection program, and the preset signal detection program is internally provided with functional modules for detecting signal strength, signal stability and signal interference. When judging the furnace top material type signal in step S2, the obtained material type signal is determined by comparing it with the preset ore and coke identifications. At the same time, when the fuzzy logic system is used to judge the furnace top material type signal, a fuzzy logic knowledge base containing detailed material characteristic parameters and corresponding fuzzy rules is synchronously constructed.

4. The method for early warning of iron surplus or deficit in a furnace according to claim 1, characterized in that: In step S3, the theoretical output per minute of top charging is calculated based on the weight of top charging and the time difference of charging.

5. The method for early warning of iron surplus or deficit in a furnace according to claim 1, characterized in that: In step S3, the minute molten iron flow rate is compared with the dynamic threshold range to determine whether the minute molten iron flow rate is a normal molten iron flow rate.

6. The method for early warning of iron surplus or deficit in a furnace according to claim 1, characterized in that: In step S3, when calculating the profit and loss iron amount in front of the furnace in this minute, the calculation formula is: the profit and loss iron amount in front of the furnace in this minute = the molten iron flow rate in minute - the theoretical output of the furnace top charging minute. Finally, when updating the cumulative profit and loss iron amount, the calculation is performed according to the formula: the profit and loss iron amount in front of the furnace = the profit and loss iron amount in front of the last furnace + the profit and loss iron amount in front of the furnace in this minute.

7. The method for early warning of iron surplus or deficit in a furnace according to claim 1, characterized in that: In the step S4, first, the warning value of the cumulative profit and loss iron amount is determined based on no less than five production tests, statistical analysis results and multi-source data, and then it is judged in real time whether the profit and loss iron amount before the furnace calculated in step S3 is greater than the warning value of the cumulative profit and loss iron amount. If it is greater, it is further judged whether there is a prompt that the profit and loss iron amount before the furnace exceeds the warning value within the previous 20 minutes. If not, it is prompted that the cumulative profit and loss iron amount before the furnace exceeds the warning value. If so, this round of judgment ends; if the profit and loss iron amount before the furnace is not greater than the warning value of the cumulative profit and loss iron amount, this round of judgment ends.

8. The method for early warning of iron surplus or deficit in a furnace according to claim 1, characterized in that: During the multi-source data collection process of step S11, temperature data at different locations in the blast furnace are collected using temperature sensors. The temperature sensors are evenly distributed at different locations inside the blast furnace, and each sensor is calibrated regularly.

9. The method for early warning of iron surplus or deficit in a furnace according to claim 1, characterized in that: When establishing a redundant channel for data transmission in step S11, the main channel and the backup channel of the redundant channel should use different transmission media. Specifically, the main channel uses optical fiber transmission, and the backup channel uses wireless transmission. At the same time, an intelligent monitoring mechanism for channel switching is set inside the redundant channel. When the data transmission of the main channel exceeds the packet loss rate, exceeds the delay, and the signal is interrupted, it automatically switches to the backup channel.

10. The method for early warning of iron surplus or deficit in a furnace according to claim 1, characterized in that: When the step S3 updates the cumulative profit and loss iron volume, a data verification mechanism is set before each update. The data verification mechanism will first check whether the data of the profit and loss iron volume in front of the furnace for this minute is within the range. If the calculated profit and loss iron volume in front of the furnace for this minute exceeds the average value of historical data, it is considered that the data is abnormal, and for abnormal data, the interpolation method is used for processing.

Images