Early warning method and system for judging abnormal furnace conditions of blast furnace based on air volume and pressure curves

Abstract

The present invention discloses an early warning method and system for judging abnormal furnace conditions of a blast furnace based on air volume and pressure curves. The method comprises: in the process of blast furnace operation, real-time collection of furnace condition characteristic data, and drawing a characteristic curve of the characteristic data changing with time; a primary judgment is made according to the change amplitude of the furnace condition characteristic data, and the primary judgment result is used to characterize whether there is a possibility of abnormality in the current furnace condition; when it is shown that there may be abnormal furnace conditions after the primary judgment, a secondary judgment is made according to the similarity between the real-time furnace condition characteristic curve and the characteristic curve under abnormal accidents, and the secondary judgment result is used to characterize the blast furnace fault type corresponding to the current abnormal furnace condition; and an abnormal early warning is made for the blast furnace condition according to the secondary judgment result. The present invention can establish a set of accident status early warning and auxiliary processing system to help blast furnace workers correctly deal with emergencies and reduce human judgment and operational errors.

Description

Technical Field

[0001] The invention belongs to the field of iron and steel metallurgy, relates to a method for predicting blast furnace conditions, and in particular to an early warning system and method for judging the nature of abnormal conditions under blast furnace accident conditions. Background Art

[0002] As a high-temperature and high-pressure continuous sealed reaction vessel, the blast furnace requires operators to make rapid and timely judgments and responses to production phenomena in the event of an accident. Once a misjudgment is made, the losses caused will be immeasurable.

[0003] In the actual production process, each blast furnace operator is affected by his own ability and quality as well as the environment, and cannot make 100% correct judgments. Especially in certain accident conditions, the loud noises and huge fluctuations in production parameters in the industrial production environment can easily bring an extreme sense of oppression and tension to the operator, which also leads to some blast furnace operators responding untimely, making operational errors and misjudgments in accident conditions. Summary of the invention

[0004] According to the above-mentioned technical problems that operators manually judge the accident status of blast furnaces, such as untimely response and easy misjudgment, an early warning method and system for judging the nature of abnormal furnace conditions of blast furnaces based on air volume and pressure curves is provided. The present invention is based on the potential correlation between air volume and pressure data and the working state of blast furnaces during the operation of blast furnaces, and automatically identifies and judges common abnormal road conditions of blast furnaces according to the working parameter combination of the blast furnace air supply system, thereby providing data support and intellectual guarantee for accurately responding to blast furnace condition accidents.

[0005] The technical means adopted by the present invention are as follows:

[0006] An early warning method for judging the nature of abnormal furnace conditions in a blast furnace based on air volume and pressure curves comprises the following steps:

[0007] During the operation of the blast furnace, real-time furnace condition characteristic data are collected, and a characteristic curve of the characteristic data changing with time is drawn, wherein the characteristic data includes fan air volume data, cold air volume data, cold air pressure data, and hot air pressure data;

[0008] Performing a primary judgment based on the change range of the furnace condition characteristic data, wherein the primary judgment result is used to indicate whether there is a possibility of abnormality in the current furnace condition;

[0009] When the primary judgment shows that there may be abnormal furnace conditions, a secondary judgment is performed based on the similarity between the real-time furnace condition characteristic curve and the characteristic curve under the abnormal accident, and the secondary judgment result is used to characterize the blast furnace fault type corresponding to the current abnormal furnace condition;

[0010] Based on the secondary judgment results, abnormal warnings are issued for the blast furnace conditions.

[0011] Furthermore, the characteristic curve under the abnormal accident is obtained according to the following method:

[0012] Establishing a furnace condition characteristic database, wherein the furnace condition characteristic database is used to store characteristic data during the operation of the blast furnace, wherein the characteristic data includes characteristic data of normal furnace conditions and characteristic data of abnormal furnace conditions;

[0013] The characteristic data of abnormal furnace conditions and the corresponding blast furnace fault types are obtained, and characteristic curves of the characteristic data changing with time under each blast furnace fault type are plotted. The blast furnace fault types include pipeline, hanging material, fan tripping and burn-through.

[0014] Furthermore, a judgment is made according to the variation range of the furnace condition characteristic data, including:

[0015] If the variation of the characteristic data exceeds a preset threshold value within any first time period, it is determined that there is a possibility of an abnormality, and the length of the first time period is preset.

[0016] Further, making a judgment based on the change range of the furnace condition characteristic data also includes:

[0017] If the cumulative change of the characteristic data exceeds a preset threshold value within any second time period, it is determined that there is a possibility of an abnormality. The length of the second time period is preset and is greater than the length of the first time period.

[0018] Furthermore, the duration of the first time period is set to 20 seconds; the duration of the second time period is set to 40 seconds.

[0019] Furthermore, the preset thresholds are set to a 5% change in air volume and a 3% change in pressure.

[0020] Furthermore, a secondary judgment is made based on the similarity between the real-time furnace condition characteristic curve and the characteristic curve under abnormal accidents, including:

[0021] The real-time furnace condition characteristic curve is compared with the characteristic curve under abnormal accidents corresponding to each blast furnace fault type. When the similarity between the real-time curve and the characteristic curve under abnormal accidents corresponding to a certain blast furnace fault type is higher than a preset threshold, it is judged that the blast furnace has the risk of this fault type occurring.

[0022] The present invention also discloses an early warning system for judging the nature of abnormal furnace conditions of a blast furnace based on an air volume and pressure curve, comprising:

[0023] A data acquisition unit, which is used to collect furnace condition characteristic data in real time during the operation of the blast furnace, and draw a characteristic curve of the characteristic data changing with time, wherein the characteristic data includes fan air volume data, cold air volume data, cold air pressure data and hot air pressure data;

[0024] A first judgment unit, which is used to make a judgment based on the change range of the furnace condition characteristic data, and the judgment result is used to indicate whether there is a possibility of abnormality in the current furnace condition;

[0025] A second judgment unit is used to make a secondary judgment based on the similarity between the real-time furnace condition characteristic curve and the characteristic curve under the abnormal accident when the furnace condition may be abnormal after the primary judgment, and the secondary judgment result is used to characterize the blast furnace fault type corresponding to the current abnormal furnace condition;

[0026] The alarm unit is used to give an abnormal warning of the blast furnace condition according to the secondary judgment result.

[0027] Compared with the prior art, the present invention has the following advantages:

[0028] The present invention utilizes the specificity of the combined characteristics of four air volume and pressure parameter curves of abnormal blast furnace conditions, establishes a database of various curve characteristics and abnormal furnace conditions through an edge-side computer, continuously collects real-time parameter curves of blast furnace production, and uses a graphics processing program to fuzzily compare the accident characteristic curve in the database with the real-time production curve, issues an early warning for the real-time production link that meets the characteristic curve, prompts the blast furnace operator of possible accident conditions, and provides directions for further inspection and processing steps.

[0029] The present invention can make early warning judgments on some accident furnace conditions, help blast furnace workers to correctly deal with sudden accidents, and reduce human operation errors. Based on the above reasons, the present invention can be widely promoted in the field of steel smelting. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0031] Figure 1 The present invention is a flow chart of an early warning method for judging the nature of abnormal furnace conditions in a blast furnace based on air volume and pressure curves in an embodiment.

[0032] Figure 2 It is a pipeline stroke characteristic curve diagram in the embodiment.

[0033] Figure 3 Graph showing the fan tripping characteristic in the embodiment.

[0034] Figure 4 It is a characteristic curve diagram of blast furnace suspended material in the embodiment.

[0035] Figure 5It is a characteristic curve diagram of air leakage of the vent valve in the embodiment.

[0036] Figure 6 It is a logic diagram of system operation in the embodiment. DETAILED DESCRIPTION

[0037] 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.

[0038] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0039] like Figure 1 As shown, the present invention provides an early warning method for judging the nature of abnormal furnace conditions of a blast furnace based on an air volume and pressure curve, comprising the following steps:

[0040] S1. During the operation of the blast furnace, real-time furnace condition characteristic data are collected, and a characteristic curve of the characteristic data changing with time is drawn. The characteristic data includes fan air volume data, cold air volume data, cold air pressure data, and hot air pressure data.

[0041] The air volume and pressure gauge of the blast furnace air supply system generally includes two systems. One is to measure the air volume and pressure on the furnace side (blast furnace side), that is, the cold air flow and hot air pressure, where the cold air flow is after the vent valve; the other is the air volume and pressure on the fan side, that is, the fan air volume and cold air pressure. Different accidents in the blast furnace will have different reactions to the apparent data of these air volume and pressure. This system uses the four parameters of cold air flow, hot air pressure, fan air volume, and cold air pressure to present different curve combinations when different abnormal furnace conditions occur, which is used to judge the nature of the abnormal furnace conditions of the blast furnace and assist the blast furnace operator in making accident predictions.

[0042] S2. Perform a judgment based on the change range of the furnace condition characteristic data, and the judgment result is used to characterize whether there is a possibility of abnormality in the current furnace condition.

[0043] Furthermore, a judgment is made according to the variation range of the furnace condition characteristic data, including:

[0044] If the variation of the characteristic data exceeds a preset threshold value during any first time period, it is determined that there is a possibility of abnormality. The first time period is preset. In the embodiment of the present invention, the first time period is preferably set to 20 seconds.

[0045] Furthermore, a judgment is made based on the change range of the furnace condition characteristic data, and further includes:

[0046] If the variation of the characteristic data in any second time period exceeds the preset threshold, it is judged that there is a possibility of abnormality. The second time period is preset and is longer than the first time period. In the embodiment of the present invention, the second time period is preferably set to 40s.

[0047] Furthermore, the preset thresholds are set to a 5% change in air volume and a 3% change in pressure.

[0048] S3. When a primary judgment shows that a furnace condition abnormality may exist, a secondary judgment is performed based on the similarity between the real-time furnace condition characteristic curve and the characteristic curve under the abnormal accident. The secondary judgment result is used to characterize the blast furnace fault type corresponding to the current furnace condition abnormality.

[0049] Furthermore, the characteristic curve under the abnormal accident is obtained according to the following method:

[0050] Establishing a furnace condition characteristic database, wherein the furnace condition characteristic database is used to store characteristic data during the operation of the blast furnace, wherein the characteristic data includes characteristic data of normal furnace conditions and characteristic data of abnormal furnace conditions;

[0051] The characteristic data of abnormal furnace conditions and the corresponding blast furnace fault types are obtained, and characteristic curves of the characteristic data changing with time under each blast furnace fault type are drawn. The blast furnace fault types include pipeline, hanging material, fan tripping and vent valve leakage.

[0052] In this embodiment, a non-human intervention characteristic curve library of abnormal accidents of blast furnaces is established on the edge side computer. Abnormal accidents include pipeline, hanging material, fan tripping and vent valve leakage, etc. Curve parameters include fan air volume, cold air volume, cold air pressure and hot air pressure. The system collects characteristic curves of four parameter combinations in the non-human interference stage before and after these accidents, such as Figures 2 to 5 , and establish an image standard database.

[0053] Furthermore, a secondary judgment is made based on the similarity between the real-time furnace condition characteristic curve and the characteristic curve under abnormal accidents, including:

[0054] The real-time furnace condition characteristic curve is compared with the characteristic curve under abnormal accidents corresponding to each blast furnace fault type. When the similarity between the real-time curve and the characteristic curve under abnormal accidents corresponding to a certain blast furnace fault type is higher than a preset threshold, the blast furnace is judged to have the risk of this fault type. Chinese patent application number 202010155640.5 discloses a curve similarity calculation method. Optionally, the present invention adopts this method to calculate the similarity between the real-time curve and the fault curve, and judges the fault type classification based on the obtained similarity result.

[0055] In this embodiment, real-time data of blast furnace production is collected by an edge-side computer, and real-time data of parameters such as fan air volume, cold air volume, cold air pressure, and hot air pressure are plotted into a curve with the same period as the feature database.

[0056] If any relevant parameter changes by more than 1% in any 20s segment or cumulatively within 40 seconds, the computer image comparison function will be triggered, and the system will continuously process the real-time curve into images for fuzzy comparison with the characteristic curve in the database. Using the system image fuzzy comparison function, the real-time production curve is continuously iterated and compared with the characteristic curve in the database. When the real-time curve is similar to a certain characteristic curve, it is determined that there is a risk of a similar abnormal accident.

[0057] S4. Issue an abnormal warning on the blast furnace condition based on the secondary judgment result.

[0058] Furthermore, after the system automatically gives a warning signal, it also provides directions for further inspection and processing steps.

[0059] The scheme and effect of the present invention are further described below through specific application examples.

[0060] like Figure 4 As shown, take the abnormal furnace condition early warning system of a 4000 cubic meter blast furnace to predict the blast furnace overhang accident as an example:

[0061] First, the real-time data of blast furnace production is collected through the edge-side computer, and the real-time data of parameters such as fan air volume, cold air volume, cold air pressure, and hot air pressure are plotted into a curve with the same period as the feature database.

[0062] When it is found that the fluctuation amplitudes of the cold air flow and hot air pressure parameters decrease by 3% and increase by 3% respectively within 20 seconds, the system image fuzzy contrast function is triggered.

[0063] The system compares the real-time curves of the four parameters with the curves in the accident characteristic curve library, and based on the image comparison results, determines that the real-time furnace condition curve is similar to the overhanging material accident characteristic curve, and gives a timely overhanging material warning, prompting the blast furnace operator to pay attention to changes in parameters such as material unloading, permeability, and top pressure, and gives relevant technical specifications for sitting material operations.

[0064] like Figure 2 As shown, take the abnormal furnace condition early warning system of a 4000 cubic meter blast furnace to predict the pipeline travel as an example:

[0065] First, the real-time data of blast furnace production is collected through the edge-side computer, and the real-time data of parameters such as fan air volume, cold air volume, cold air pressure, and hot air pressure are plotted into a curve with the same period as the feature database.

[0066] When it is found that the fluctuation range of the two parameters of cold air flow and hot air pressure increases by 5% and decreases by more than 3% respectively within 20 seconds, the system image fuzzy contrast function is triggered.

[0067] The system compares the real-time curves of the four parameters with the curves in the accident characteristic curve library, and based on the image comparison results, determines that the real-time furnace condition curve is similar to the pipeline accident characteristic curve, and gives timely pipeline warnings, prompting blast furnace operators to pay attention to changes in parameters such as top pressure and material unloading, and gives operational suggestions for related control of pipeline travel such as reducing air and oxygen.

[0068] like Figure 3 As shown, take the abnormal furnace condition early warning system of a 4000 cubic meter blast furnace predicting the fan tripping accident as an example:

[0069] First, the real-time data of blast furnace production is collected through the edge-side computer, and the real-time data of parameters such as fan air volume, cold air volume, cold air pressure, and hot air pressure are plotted into a curve with the same period as the feature database.

[0070] When it is found that the cold air flow and hot air pressure parameters drop by 5% and 3% or more respectively within 20 seconds, the system image fuzzy contrast function is triggered.

[0071] The system compares the real-time curves of the four parameters with the curves in the accident characteristic curve library, and based on the image comparison results, determines that the real-time furnace condition curve is similar to the fan tripping accident characteristic curve, and promptly gives a fan tripping warning, prompting the blast furnace operator to pay attention to changes in parameters such as cold air pressure, fan air volume, and tuyere status, and gives relevant operational suggestions such as preventing gas leakage and slag filling.

[0072] like Figure 5 As shown, take the abnormal furnace condition early warning system of a 4000 cubic meter blast furnace predicting the air leakage accident of the vent valve as an example:

[0073] First, the real-time data of blast furnace production is collected through the edge-side computer, and the real-time data of parameters such as fan air volume, cold air volume, cold air pressure, and hot air pressure are plotted into a curve with the same period as the feature database.

[0074] When it is found that the fluctuation range of the two parameters of cold air flow and fan air volume decreases by 5% and increases by more than 5% respectively within 20 seconds, the system image fuzzy contrast function is triggered.

[0075] The system compares the real-time curves of the four parameters with the curves in the accident characteristic curve library, and based on the image comparison results, determines that the real-time furnace condition curve is similar to the vent valve leakage accident characteristic curve, and promptly gives a vent valve leakage warning, prompting the blast furnace operator to pay attention to changes in parameters such as cold air flow and fan air volume, and gives relevant operational suggestions such as preventing gas cross-flow and slag filling.

[0076] The present invention also discloses an early warning system for judging the nature of abnormal furnace conditions of a blast furnace based on an air volume and pressure curve, comprising:

[0077] A data acquisition unit, which is used to collect furnace condition characteristic data in real time during the operation of the blast furnace, and draw a characteristic curve of the characteristic data changing with time, wherein the characteristic data includes fan air volume data, cold air volume data, cold air pressure data and hot air pressure data;

[0078] A first judgment unit, which is used to make a judgment based on the change range of the furnace condition characteristic data, and the judgment result is used to indicate whether there is a possibility of abnormality in the current furnace condition;

[0079] A second judgment unit is used to make a secondary judgment based on the similarity between the real-time furnace condition characteristic curve and the characteristic curve under the abnormal accident when the furnace condition may be abnormal after the primary judgment, and the secondary judgment result is used to characterize the blast furnace fault type corresponding to the current abnormal furnace condition;

[0080] The alarm unit is used to give an abnormal warning of the blast furnace condition according to the secondary judgment result.

[0081] As for an embodiment of the early warning system for judging the nature of abnormal condition of a blast furnace based on air volume and wind pressure curves of the present invention, since it corresponds to the above embodiment of the early warning method for judging the nature of abnormal condition of a blast furnace based on air volume and wind pressure curves, the description is relatively simple. For relevant similarities, please refer to the partial description in the above embodiment of the early warning method for judging the nature of abnormal condition of a blast furnace based on air volume and wind pressure curves, which will not be described in detail here.

[0082] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. An early warning method for judging the nature of abnormal furnace conditions of a blast furnace based on air volume and pressure curves, characterized in that: The following steps are involved: During the operation of the blast furnace, the furnace condition characteristic data is collected in real time, and the characteristic curve of the combination of four air volume and air pressure parameters, namely, the fan air volume data, the cold air volume data, the cold air pressure data and the hot air pressure data, which changes with time is drawn; the cold air volume data and the hot air pressure data are obtained from the furnace inlet side, and the fan air volume data and the cold air pressure data are obtained from the fan side; Performing a judgment based on the change range of the furnace condition characteristic data, wherein the result of the judgment is used to indicate whether there is a possibility of abnormality in the current furnace condition; When the primary judgment shows that there may be abnormal furnace conditions, a secondary judgment is performed based on the similarity between the real-time furnace condition characteristic curve and the characteristic curve under the abnormal accident, and the result of the secondary judgment is used to characterize the blast furnace fault type corresponding to the current abnormal furnace condition; Based on the results of the secondary judgment, an abnormal warning of the blast furnace condition is issued.

2. The early warning method for judging the nature of abnormal furnace conditions of a blast furnace based on air volume and pressure curves according to claim 1 is characterized in that: The characteristic curve under the abnormal accident is obtained according to the following method: Establishing a furnace condition characteristic database, wherein the furnace condition characteristic database is used to store characteristic data during the operation of the blast furnace, wherein the characteristic data includes characteristic data of normal furnace conditions and characteristic data of abnormal furnace conditions; The characteristic data of abnormal furnace conditions and the corresponding blast furnace fault types are obtained, and characteristic curves of the characteristic data changing with time under each blast furnace fault type are plotted. The blast furnace fault types include pipeline, hanging material, fan tripping and burn-through.

3. The early warning method for judging the nature of abnormal furnace conditions of a blast furnace based on air volume and pressure curves according to claim 1 is characterized in that: Make a judgment based on the change range of furnace condition characteristic data, including: If the variation of the characteristic data exceeds a preset threshold value within any first time period, it is determined that there is a possibility of an abnormality, and the duration of the first time period is preset.

4. The early warning method for judging the nature of abnormal furnace conditions of a blast furnace based on air volume and pressure curves according to claim 3 is characterized in that: A judgment is made based on the change range of the furnace condition characteristic data, which also includes: If the cumulative change amplitude of the characteristic data exceeds a preset threshold value within any second time period, it is determined that there is a possibility of an abnormality. The length of the second time period is preset and is greater than the length of the first time period.

5. The early warning method for judging the nature of abnormal furnace conditions of a blast furnace based on air volume and pressure curves according to claim 4 is characterized in that: The duration of the first period is set to 20 seconds; the duration of the second period is set to 40 seconds.

6. The early warning method for judging the nature of abnormal furnace conditions of a blast furnace based on air volume and pressure curves according to claim 4 is characterized in that: The preset threshold is set to a variation range of 1%.

7. The early warning method for judging the nature of abnormal furnace conditions of a blast furnace based on air volume and pressure curves according to claim 1, characterized in that: A secondary judgment is made based on the similarity between the real-time furnace condition characteristic curve and the characteristic curve under abnormal accidents, including: The real-time furnace condition characteristic curve is compared with the characteristic curve under abnormal accidents corresponding to each blast furnace fault type. When the similarity between the real-time curve and the characteristic curve under abnormal accidents corresponding to a certain blast furnace fault type is higher than a preset threshold, it is judged that the blast furnace has the risk of this fault type occurring.

8. An early warning system for judging the nature of abnormal furnace conditions in a blast furnace based on air volume and pressure curves, characterized in that: include: A data acquisition unit is used to collect furnace condition characteristic data in real time during the operation of the blast furnace, and draw a characteristic curve of the combination of four air volume and pressure parameters, namely, fan air volume data, cold air volume data, cold air pressure data and hot air pressure data, changing over time; A first judgment unit, which is used to make a judgment based on the change range of the furnace condition characteristic data, and the result of the judgment is used to indicate whether there is a possibility of abnormality in the current furnace condition; A second judgment unit is used to make a secondary judgment based on the similarity between the real-time furnace condition characteristic curve and the characteristic curve under the abnormal accident when the furnace condition may be abnormal after the primary judgment, and the result of the secondary judgment is used to characterize the blast furnace fault type corresponding to the current abnormal furnace condition; The alarm unit is used to give an abnormal warning of the blast furnace condition according to the result of the secondary judgment.

Images