JPS63297516A - Method for predicting lowering of furnace temperature in blast furnace - Google Patents

Abstract

PURPOSE:To rapidly and surely measure lowering of furnace temp. in a blast furnace by using measurement of temp. differences on the furnace inner wall every prescribed time interval with plural inner wall thermometers arranged in the blast furnace together with measurements of solution loss carbon quantity and N2 concn. by analyzing the top furnace gas. CONSTITUTION:The inner wall thermometers 3 of total 28 pieces - four pieces in a circumferential direction and seven pieces in a vertical direction - in the blast furnace 1 are buried and the temp. differences of the inner wall are measured ever prescribed time interval. Then, when the sum of the positive values in the temp. differences exceeds the setting value or when the sum of the negative values exceeds the setting value or when the sum of moving average values showing the positive values in the temp. difference of the inner wall exceeds the setting value, the lowering of the furnace temp. is primarily predicted. Next, further by predicting that the moving average value of the solution loss quantity of coke in the furnace and the moving average value of the N2 gas concn. in the top furnace gas exceed respectively the setting values, the lowering of the furnace temp. is secondarily judged and the temp. raising treatment is executed, and aggravation of the furnace condition caused by lowering of the furnace temp. in the blast furnace is prevented.

Description

DETAILED DESCRIPTION OF THE INVENTION <Industrial Application Field> The present invention relates to a method for predicting heat drop in a blast furnace for stable operation of a blast furnace.

(Prior art and its problems) It has been known for a long time that in order to maintain stable operation of a blast furnace, it is necessary to keep the temperature of hot metal constant. For this reason, blast furnace operators have always needed to predict changes in blast furnace heat.

^ When it comes to changes in furnace heat, predicting the temperature drop is extremely important, especially since a drop in temperature may solidify the hot metal and prevent it from flowing out of the blast furnace.

As a method for predicting blast furnace furnace heat, Japanese Patent Application Laid-Open No. 60-39107
There are some that have been disclosed. This method is based on the viewpoint that the charge temperature around the furnace belly has a strong correlation with the hot metal temperature.
As shown in FIG. 13, the relationship between the temperature in the local area of the blast furnace 1 detected by the sensor (belly probe) 2 and the hot metal temperature is subjected to linear regression as shown in FIG. 14. Based on this linear equation, the hot metal temperature Tpig is calculated from the local temperature in the furnace abdomen.
It predicts.

However, with this method, it is necessary to insert the furnace probe 2 in order to measure the temperature near the inner wall of the furnace, and therefore temperature measurement can only be carried out intermittently, which naturally deteriorates the accuracy of predicting the temperature of the hot metal. There was a problem with this.

Further, even if the hot metal temperature is the same, the furnace temperature may change due to changes in the production plan, raw material charging conditions, etc. Therefore, the linear equation based on the absolute value of the furnace wall temperature shown in FIG. 14 has the problem that accurate prediction cannot necessarily be made.

On the other hand, conventionally, the amount of solution loss carbon (hereinafter referred to as [Tsuru Loss CIJ]) indicates the quality of the reduction state of the blast furnace.
Another prediction method is to predict the blast furnace heat based on the increase or decrease of . An increase in the amount of Turuloss C indicates that the so-called Turuloss reaction described below is promoted.

C+ G O2→ 2CO Since this reaction is an endothermic reaction, it can be predicted that the blast furnace heat will decrease.

The amount of truss loss C is calculated by measuring the amount of (7) Go, Co2. It is calculated based on the amount of N2 paste, air blowing conditions, and raw material charging conditions, and conventionally, the decrease in furnace heat was managed by the average value of the amount of vine loss C every hour.

In FIGS. 15(a) and (b), (a) t;
t, the amount of turret loss C every 3 minutes (j!1), and the time-dependent changes in the turret loss CI average 11 [12] every hour.
) is a graph showing changes in hot metal temperature over time. In the figure, although the threshold value ε1 is exceeded at time 17, no action is taken to raise the temperature, and thereafter the hot metal temperature drops significantly as shown in (■). FIG. 16 shows the respective changes over time when the gastric fever action A occurred at time 13:00 when the threshold value ε2 was exceeded. Similarly to Fig. 15, 11 in the figure indicates the instantaneous MiI every 3 minutes.
12 indicates the hourly average Truloss CI. 15th
figure.

By comparing Fig. 16, it can be seen that the hot metal temperature decrease as shown in ■ in Fig. 15 (1)) due to heat action A is caused by the first
As shown in Figure 6, it can be seen that this can be avoided to some extent.

However, when predicting the average value of the crane loss CI every hour, there is a problem that when there is a sudden increase in the crane loss (I), in the worst case, there is a delay in predicting the decrease in furnace heat by about an hour. For example, in the case of Fig. 16, wild heat action A is not taken until the hot metal temperature has fallen below the control temperature Tc to a certain extent due to the prediction delay.

Therefore, in order to avoid this problem, when predicting the decrease in furnace heat using the instantaneous values of the truss loss CI measured at intervals of about 3 minutes, individual variations are large, as shown in 11 in Figures 15 and 16. , data is not sustainable due to large noise components. Therefore, it is almost impossible to predict the decrease in furnace heat using the instantaneous value of the amount of truss loss C.

(Object of the Invention) An object of the present invention is to provide a blast furnace furnace heat drop prediction method that can solve the problems of the prior art described above, obtain predictions as quickly as possible, and accurately predict the drop in hot metal temperature. That's true.

(Means for Achieving the Object) In order to achieve the above object, the blast furnace heat drop prediction method according to the present invention includes installing an inner wall thermometer at a predetermined location of the blast furnace,
The inner wall temperature difference is measured at predetermined time intervals using the inner wall thermometer, and when the total value of the positive value of the inner wall temperature difference at a certain time exceeds a predetermined value, the blast furnace furnace heat decreases. and a second prediction means that predicts that the blast furnace heat will decrease when the total value of the negative value of the inner wall temperature difference at a certain time exceeds a predetermined value. and a third prediction means for predicting that the blast furnace heat will decrease when the sum of moving average values over a predetermined time width of the portion showing a positive value of the inner wall temperature difference at a certain time exceeds a predetermined value 1a. and calculating the solution loss carbon S at predetermined time intervals, and when the moving average value of the calculated values in the predetermined time width exceeds the predetermined value, the blast furnace A fourth prediction means for predicting a decrease in furnace heat; a fourth prediction means for calculating the amount of nitrogen in the furnace top gas component at predetermined time intervals; The method is equipped with at least one of the prediction means for predicting the blast furnace furnace heat drop when the temperature exceeds the temperature, and the prediction is made by any one of the first prediction means to the third prediction means. The blast furnace heat drop is finally predicted only when the fourth prediction means or the fifth prediction means makes a prediction within a later predetermined period.

(Example) A. First Reason for Reduction in Furnace Heat The following factors can be considered as causes for the reduction in furnace heat of the blast furnace.

High-temperature air (gas flow) blown from the blast furnace tuyeres to adjust the temperature of the molten metal and the amount of hot metal is usually blown into the center of the furnace. However, the raw material charging conditions are 1! Due to reasons such as the distribution of materials in the furnace, a large amount of gas may suddenly flow to the periphery of the furnace. As a result, the endothermic reaction of Fe O+C-)Fe 10 GO is promoted and the furnace heat decreases.

By the way, when the gas flow flows around the furnace, Na
, when the deposits in the furnace such as Pb and the stagnation layer peel off and fall off the wall, the temperature of the furnace wall in that part increases rapidly. If this rapid temperature rise is detected, a decrease in furnace heat can be predicted.

B. Second Reason for Decrease in Furnace Heat The following may be considered as a cause of the decrease in furnace heat in the blast furnace.

If the unloading speed in the blast furnace increases for the same reason as N4,
The level of the cohesive zone in the blast furnace decreases due to so-called raw ore descent, causing a decrease in furnace heat.

By the way, when the cohesive zone level decreases, the furnace wall temperature at the corresponding portion also decreases rapidly. If this sudden temperature failure is detected, a decrease in furnace heat can be predicted.

C3 Third Reason for Decrease in Furnace Heat Furthermore, the following may be considered as a contributing factor to the decrease in furnace heat in the blast furnace.

High-temperature air (gas flow) blown up from the blast furnace tuyeres to adjust the temperature and amount of hot metal is usually blown into the center of the furnace. However, for the same reason as Flies 1, part of the gas flow may flow to the periphery of the furnace. If this state continues for a long time, heat dissipation from the gas flow from the blast furnace wall becomes greater than during normal operation, resulting in a decrease in furnace heat.

By the way, when a part of the gas flow steadily flows into the periphery of the furnace, the temperature of the furnace wall gradually increases. If such a gradual temperature rise over a relatively long period of time is detected, a decrease in furnace heat can be predicted.

D. First to Third Predicting Means FIGS. 1(a) and 1(b) are a side sectional view and a plan sectional view, respectively, showing the arrangement of an inner wall thermometer used in an embodiment of the present invention. As shown in the figure (a), the inner wall thermometer 3
7 pieces in the height direction of blast furnace 1 (3 pieces on the back).

(2 abdominal parts, 2 morning glory parts), and 4 pieces are installed in the circumferential direction of the blast furnace 1 as shown in FIG. In other words, a total of 28 inner wall thermometers 3 are installed in four directions and seven levels.

For example, the internal temperature meter was developed by the present applicant in Utility Model Application No. 57-81.
531. The one disclosed in Japanese Utility Model Publication No. 59-16816 may be used, and FIG. 2 is a conceptual diagram showing the inner wall thermometer (hereinafter referred to as "rFM sensor") disclosed in the latter.

In the figure, reference numeral 4 denotes a sheath type thermometer having two conductive wires 5 buried in parallel insulatively and having a temperature sensing part 6 on the front end side. The temperature-sensing parts 6 are arranged in parallel so that they are arranged at different lengthwise positions, and a sheath-type dummy rod 7 is connected to the tips of the temperature-sensing parts 6 to align the leading ends. The sheath type dummy rod 7 has two conductors 115 buried in parallel insulatively, and has substantially the same thermal conductivity as the sheath type temperature measuring element 4. FM sensor 3
is formed by keeping the sheath type temperature measuring elements 4 not connected to each other with an insulating material 8 and storing them in a sheath tube 9.

FIG. 3 is an explanatory diagram of the installation of the FM sensor 3. In the figure, 10 to 13 are the walls of the blast furnace, 10 is a brick, and 1
1 is a stave, 12 is a stamp, and 13 is an iron skin. F
As shown in the figure, the M sensor 3 is installed inside the furnace wall by welding to a packing 14 and a welded portion 15. Note that 16 is a filler, and 17 is a milk injection port into which the filler 16 is poured.

Note that due to the installation and structure of the FM sensor 3 described here, the FM sensor 3 itself is eroded along with the erosion of the furnace wall, and the sheath type temperature sensing element 4 may be exposed inside the furnace near the furnace wall. In addition to "furnace wall temperature", "furnace temperature near the furnace wall"
is being measured. Hereinafter, a concept including both will be described as "furnace wall temperature." As mentioned above, compared to conventional thermometers such as sheathed thermocouples, the FM sensor 3 has a large number of measurement points, satisfies rapid temperature measurement response, is capable of long-term continuous temperature measurement, and is highly reliable. The aim is to improve performance, durability, and workability.

Each FM sensor 3 measures the inner wall temperature of the blast furnace 1 at every predetermined sampling time Δt, as shown in FIG. Here, the inner wall temperature of the first FM sensor 3 at time j is Tj
, i, and one sampling time Δ at time j is the previous inner wall temperature T・, then 1.3-1. + T1. and T, , which inner wall temperature difference (difference 1) ΔTJ,
l J-1,1... is J,1 ΔTj, l =Tj,i -"j-1,i ・
...(1). This state is shown in FIG.

This difference value ΔTj, , is multiplied by a weight W, taking into consideration the height of each FM sensor 3 in two circumferential directions, etc. Roughly speaking, the difference value Δ
For those where Tj, , is negative, V.

=0, and for other values, v is also multiplied by a positive/negative parameter v1 indicating =1 to obtain a corrected difference value (positive difference value) CTj at time j.

CT,, -w--v -ΔT,, -(2
) J, I I i J, 1
Next, the sum of the corrected difference values CTj, , for all FM sensors 3 is calculated, and this sum is set as 5T1j.

ST1, - Σ CT・,
・-(3) J i, (JA) According to the following equation (4), if the value of the total difference value 5T1j becomes larger than the predetermined threshold ε1, it is assumed that the furnace wall is suddenly damaged due to wall fall of deposits inside the furnace. Assuming that there has been a temperature rise, the first prediction means predicts a decrease in furnace heat.

ST1·≧ε1 (4) The above is the first prediction means based on the reason A.

The second prediction means based on the reason B is as shown below.

In equation (2), the positive and negative parameters Vi are the difference values 6 to 1
．． For those where is positive, v,=Q, and for those other than J,1, set ■H-i, and then calculate the absolute value of the corrected difference value CTj, for all FM sensors 3. Take the total sum and call it 5T2j.

Ko? 5T2j″″, %, l CTj, 1 l °−
(3)' Then, according to the next equation (4) °, if the value of the total difference value 5T2j based on the equation (3) becomes larger than the predetermined threshold ε2, it is assumed that there has been a rapid temperature drop due to the raw ore descent, The second prediction means predicts the decrease in furnace heat.

ST2・≧ε2...(4)
.

Ω. The third prediction means based on the reason is as shown below.

Is the positive/negative parameter ■ in equation (2) the first prediction means? Similarly, for negative difference values ΔTj, , v,
=Q, and for other cases ■, =1. Also, at time j, the correction difference value before the sampling time (that is, before ΔtXk time) is set as CT j-.

Then, for all FM sensors 3 of the value at time j of the moving average of this corrected difference value with a predetermined time width nΔt... (3)
” Then, according to the following formula (4), this moving average sum 5T3j
If the value becomes larger than a predetermined threshold value ε3, it is assumed that there has been a gradual temperature rise for a long period of time, and the third prediction means predicts a decrease in furnace heat.

ST3・≧ε3...(4)"Since the above-mentioned first to third prediction means are each performed based on the furnace wall temperature difference (difference value), Accurate predictions can be made.Moreover,
The FM sensor 3 can be arranged to cover the entire circumference of the blast furnace due to its good workability and good temperature measurement response, and by being able to grasp continuous inner wall temperature differences, more accurate predictions can be made.

Further, the first to third prediction means described above can be realized by a computer. FIG. 6 is a flowchart showing the processing flow of the first prediction means. In the figure, in step S1, the furnace wall temperature Tj of each FM sensor 3 is measured at every sampling time Δ. Next, in step S2, the difference value of each FM sensor 3 is calculated based on equation (1).

Then, in step S3, a total positive difference value 5T1j is determined based on equations (2) and (3). Furthermore, in step S4, this positive difference value sum ST1 is compared with a predetermined threshold value ε1, and if the equation (4) is satisfied, in step S5, the furnace heat decreases due to rapid peripheral flow of the gas flow. It is assumed that this will occur and an alarm is output. On the other hand, if the equation (4) is not satisfied, it is assumed that there is no abnormality and the process returns to step S1, whereupon steps 81 to S4 are repeated to predict a decrease in furnace heat.

FIG. 7 is a flowchart showing the process flow of the second prediction means. In the figure, in step S11, the furnace wall temperature Tj, , of each FM sensor is measured at every sampling time Δ. Next, in step S12, each FM sensor 3
Calculate the difference value based on equation (1).

Then, in step 813, (2)', (3)'
The total negative difference value ST2 is calculated based on the formula. Furthermore, in step 814, this negative difference value sum ST2
* is compared with a predetermined threshold value ε2, and if equation (4) is satisfied, it is assumed that a decrease in furnace heat will occur due to the increase in unloading speed in step 815, and an alarm is output. On the other hand, if the equation (4) is not satisfied, it is assumed that there is no abnormality, and the process returns to step 811, and the furnace heat decrease is predicted by repeating steps 811 to S14.

FIG. 8 is a flowchart showing the processing flow of the third prediction means. In the figure, in step $21, the furnace wall temperatures Tj and H of each FM sensor 3 are measured at every sampling time Δ. Next, in step S22, the difference value of each FM sensor 3 is calculated based on equation (1).

Then, in step S23, (2)", (3)"
The moving average sum 5T3j of the positive difference values in the time width nΔt is determined based on the formula. Furthermore, in step 824, this positive difference value moving average sum 5T3j is compared with a predetermined threshold value ε3, and if formula (4) is satisfied, in step 825, the furnace heat decreases due to furnace body heat dissipation. outputs an alarm. On the other hand, (
4) If the formula is not satisfied, it is assumed that there is no abnormality and the process returns to step 821, and the following steps 821 to 824 are performed.
By repeating this, the decrease in furnace heat is predicted.

E, 4th. Fifth prediction means The amount of vine loss C (Ky/
l-p) is calculated for each sampling time Δt. Here, the amount of trail loss C at time j is set to X, and time j
If the amount of true loss C before the sampling time (i.e., ΔtXk time) is X j−H, then the current time j
The moving average xH of the predetermined time width nΔt in can be calculated as follows.

xH based on equation (5) is calculated for each sampling time Δt, and when XH exceeds a predetermined threshold ε, an alarm is issued and a decrease in furnace heat is predicted using equation (6) below.

xH>ε8 (6) The above is the fourth prediction means.

In addition, N2ff1 (%) in the furnace top gas detected by gas chromatography (hereinafter referred to as "gas chromatography N2 amount") has a strong negative correlation with the amount of truss loss C; A decrease in blast furnace heat can be predicted by a decrease in the amount of N2.

As a result, the gas chromatography N2 mother at the current time j is set to yj, and the gas chromatography Nil at the sampling time before time j (that is, Δtxk hours before) is '/j-H
Then, the moving average yH of the predetermined time width nΔt at the current time j can be calculated as follows: yH−” yj−k n+1 μ′ (1).

yH based on equation (7) is calculated at every sampling time Δ, and when y14 falls below a predetermined threshold ε, an alarm is issued and a decrease in furnace heat is predicted using equation (8) below.

y,<ε, (8) The above is the fifth prediction means.

° Furthermore, when calculating the moving average of the trail loss Cff1, which is the fourth prediction means, it is assumed that the instantaneous value of the trail loss C amount is the 9th
As shown in Figure (a), the abnormal value E1. E
2 may occur. Here, the turrus C at time j
ff1 is x, 1 sampling time Δ is the previous trail loss C
If the quantity is X, then the absolute value Δ of the difference value of the 0s C quantity is
X J is Δx, -1x=-x, l ・ (9
) J J J-1. By comparing this ΔX with the threshold value ε7 as shown in the same figure (b), the abnormal value E1. Find E2 and draw the same figure (C
), a method of smoothing by replacing it with the immediately previous measured value can be considered. By applying this method, a more accurate moving average of the true loss Cff1 can be obtained, and as a result, prediction with considerably high accuracy is possible.

A method for predicting a decrease in furnace heat by using a moving average of the true loss Cfi, which includes such an abnormal value correction, can be realized using a computer. FIG. 10 is a flowchart showing the flow of the process. In the same figure, step 8
31, the instantaneous value
Find each time. Then, in step 832, the absolute value ΔXJ of the difference value of the true loss CI is determined, and then in step 8
If the absolute value ΔX of the difference value is larger than the threshold ε2 in step 833, then in step 834 this instantaneous value
J is regarded as an abnormal value and replaced with the immediately previous measured value Xj-1, and the process moves to step S35. On the other hand, if it is smaller than the threshold ε, the process moves to step S35 without changing the instantaneous value xj. In step S35, the moving average x8 of the time width nΔt is calculated, and in the next step S36, it is compared with the threshold value ε8. If the moving average XH exceeds the threshold value ε8, it is assumed that a decrease in blast furnace heat has occurred, and an alarm is output in step S37. On the other hand, if the moving average XH is below the threshold value ε8, it is determined that there is no abnormality, and the process returns to step S31 again to predict a decrease in furnace heat by repeating steps 831 to S36.

Note that, of course, the above-mentioned abnormal value processing.

Application to a computer can be similarly realized in the case of predicting a decrease in furnace heat using the moving average value VH of gas chromatography N2m.

4. mentioned above. Since the fifth prediction means is based on a moving average for each sampling time Δ, prediction can be obtained quickly and the accuracy can be said to be sufficiently reliable.

F. Comprehensive prediction means Dl - By using the first to fifth prediction means described in 2 above, comprehensive prediction is performed as described below.

First, it is checked whether a decrease in the furnace heat is predicted by any of the first to third prediction means, and if even one predicts a decrease in the furnace heat, the subsequent predetermined Duration (about 2 hours) 4th. Let's focus on the fifth prediction means. Then, during this predetermined period, the fourth. When any of the fifth prediction means predicts that the furnace heat will decrease, it is assumed that the blast furnace furnace heat decrease will occur as a final comprehensive prediction, and an alarm is output.

FIG. 11 is a flowchart showing the processing flow of this comprehensive prediction means. This will be explained below with reference to the same figure.

In step 841, the first to fifth prediction means are performed in parallel.

Then, in step 84.2, the fourth. Focusing on the prediction results of the first to third prediction means, which have higher foresight (predictions can be obtained faster) than the fifth prediction means, until a decrease in furnace heat is predicted by any of these prediction means, Attention will be paid to the prediction results of the first to third prediction means. Then, when at least one of the first to third prediction means predicts that the furnace heat will decrease, in step 843, the fluctuation time t is set to t.

= 0, and at the same time set the hold time (about 2 hours).

Next, in step S44, the fluctuation time tc becomes the hold time,
Check to see if it has been exceeded. This means that after a prediction of a decrease in furnace heat is made by any one of the first to third prediction means, a prediction of a decrease in furnace heat is made by one of the fourth and fifth prediction means within the hold time hr. This is to output an alarm as a comprehensive prediction when the prediction is made. Therefore, the variation time t
If C exceeds the hold time, the process returns to step 842 and attention is again paid to the prediction results of the first to third prediction means. If the variation time tc does not exceed the hold time hr, the process moves to the next step S45.

In step 345, the fourth. Paying attention to the fifth prediction means, if a decrease in furnace heat is predicted by any of them, step 8
At step 46, an alarm is output and a decrease in furnace heat is predicted as a final comprehensive prediction. On the other hand, the 4th. If the fifth prediction means does not predict a decrease in the heat of both co-cores, the process returns to step 844 and it is checked again whether the variation time tc exceeds the hold time tc.

FIG. 12 is a graph showing an operation example of the comprehensive prediction means described above, in which (a) is the hot metal temperature, (b) is the sum of positive difference values (first prediction means), and (C) is the amount of gas chromatin N2 ( 5 is a graph showing changes over time of the fifth prediction means). In addition, the same figure (a
) is the actual temperature measured approximately every 30 minutes during tapping into the hot metal 1) till pot (1 tap approximately 2 hours), and approximately 3 Q minutes between tapping and the next tap. It is an intermittent iron that is left in place. Furthermore, when a 1fi decrease in hot metal temperature is observed, action is taken to raise the furnace heat. In the figure, 1 scale indicates 100 minutes. is the control temperature. A in the same figure (b)
1, a prediction of a decrease in furnace heat was made using the first prediction means. For the next two hours, attention was paid to the prediction means in box 5, and at 81 in the same figure (C), a prediction that the furnace heat would decrease was made by the fifth prediction means, and at this point, it was determined for the first time as a comprehensive prediction that the furnace heat would decrease. It outputs an alarm. The invasion diagram (a
), it can be seen that the hot metal temperature has clearly decreased.

In addition, in FIG. 12, the 2nd, 3rd, and 3rd stages are shown simply for convenience of explanation. Fourth, the results of the prediction means are simply not shown.

Here, the OR prediction that predicts a decrease in furnace heat when any of the first to third prediction means is established is changed to prediction 1, 4. Fifth
Assuming that Prediction B is the OR prediction that predicts the furnace heat drop when any of the prediction means holds true, Prediction A, Prediction B, and the above-mentioned comprehensive prediction are based on the results of experiments and the prediction rates (number of alarms) shown in Table 1. /number of times the furnace temperature decreased) and false alarm rate (number of alarm errors/total number of alarms) were found to be obtained.

Table 1 As is clear from Table 1, there is little decrease in the forecast rate in the comprehensive forecast, and it can be seen that the false alarm rate is greatly reduced.

G. Supplementary note: In the first to third prediction means in this example, an FM sensor was used as the inner wall thermometer, but a normal temperature sensor (for example, a sheathed thermocouple) can also be used as a substitute, although it has problems with its lifespan. It is possible. Furthermore, a stave thermometer or a brick-embedded thermometer can be used as a substitute, although the prediction accuracy will be slightly lower due to their reliability and low temperature response.

Furthermore, in the first to third prediction means in this example,
Although 28 FM sensors 3 were installed in 7 levels and in 4 directions, it goes without saying that they may be installed appropriately depending on the characteristics of the blast furnace.

(Effects of the Invention) As explained above, according to the present invention, a prediction can be obtained quickly, and a decrease in hot metal temperature can be predicted more accurately because it is based on a comprehensive judgment of the first to fifth prediction means. .

[Brief explanation of drawings]

FIGS. 1(a) and 3(b) are a side sectional view and a plan sectional view, respectively, showing the arrangement of an FM sensor used in an embodiment of the present invention in the blast furnace wall, and FIGS. 2 and 3 are respectively FM sensor conceptual diagram, installation explanatory diagram, Fig. 4 is a graph showing the change over time in the furnace wall temperature measured by the FM sensor, Fig. 5 is a graph showing the change over time in the difference value of the furnace wall temperature measured by the FM sensor, 6
7 is a flowchart showing the process flow of the second prediction means. FIG. 8 is a flowchart showing the process flow of the third prediction means. Figures 9 (a), (b), and (c) are the instantaneous value of the trail loss Cff1 including abnormal values, the absolute value of the difference value of the trail loss C amount, and the trail loss C after removing the abnormal values, respectively.
Graph showing the instantaneous value of ff1, FIG. 10 is a flowchart showing the processing flow of the fourth prediction means, FIG. 11 is a flowchart showing the processing flow of the comprehensive prediction means, and FIGS. 12(a), (b) , (c) are graphs showing the changes over time in the hot metal temperature, the total positive difference value, and the amount of gas chromatin N2, respectively; FIG. 13 is a side sectional view showing the arrangement of the furnace belly sonde in the blast furnace in the conventional technology; FIG. 14 Figure 15 (a) is a graph showing the correlation between hot metal temperature and furnace side layer temperature, Figure 15 (a) is a graph showing the hourly average value of the amount of trunnion C and the change in hot metal temperature over time, Figure 16 (a), (b) is a graph showing the 1-hour average value of the amount of truss loss C and the change over time in the hot metal temperature when the heating action is performed.

Claims (1)

[Claims] (1) An inner wall thermometer is installed at a predetermined location in the blast furnace, and the inner wall temperature difference is measured at a predetermined time interval with the inner wall thermometer, and the sum of the portions that show a positive value of the inner wall temperature difference at a certain time. a first prediction means for predicting a blast furnace furnace heat drop when the value exceeds a predetermined value; and a predetermined value in which the total value of the portion indicating a negative value of the inner wall temperature difference at a certain time The second method predicts that the blast furnace heat will decrease when the
and a third means for predicting a blast furnace heat drop when the sum of moving average values over a predetermined time width of the portion showing a positive value of the inner wall temperature difference at a certain time exceeds a predetermined value. and calculating the solution loss carbon amount at each predetermined time interval, and the moving average value of the calculated value in the predetermined time width is
A fourth prediction means predicts that the blast furnace heat will decrease when the temperature exceeds a predetermined value; Further comprising at least one of a fifth prediction means for predicting a blast furnace heat drop when the moving average value exceeds a predetermined value, and the first to third prediction means When the prediction of the fourth prediction means or the fifth prediction means is made within a predetermined period after the prediction is made by either of the above,
A blast furnace heat drop prediction method that finally predicts the blast furnace heat drop for the first time.