Method for discovering abnormal temperature rise of wall body in time in operation process of blast furnace

Abstract

The invention provides a method for discovering abnormal temperature rise of a wall body in time in the operation process of a blast furnace. The method comprises the following steps: determining a temperature normal operation period time period and a temperature abnormal operation period time period according to the fluctuation degree of a temperature time sequence scatter diagram in different time periods; randomly screening out a plurality of temperature data from the temperature abnormal operation time period as a statistical sample of the blast furnace early warning interval; according to the data distribution type of the blast furnace early warning interval statistical sample, determining a temperature early warning upper limit value of blast furnace cooling wall body temperature operation; and judging whether the wall body temperature is abnormal or not according to the temperature early-warning upper limit value of blast furnace cooling wall body temperature operation. Based on the principle of statistics, the alarm conditions are established according to the temperature fluctuation conditions of the cooling wall of the blast furnace in different time periods, workers can be reminded in real time to take corresponding measures in time, the risk of equipment damage is reduced, and the maintenance and shutdown cost of the blast furnace is reduced.

Description

Technical Field

[0001] The invention relates to the technical field of blast furnace smelting, and in particular to a method for timely detecting abnormal increase in wall temperature during operation of a blast furnace. Background Art

[0002] Blast furnaces are important equipment for iron ore reduction in the metallurgical industry. Their operating efficiency and safety directly affect production costs and economic benefits. Temperature monitoring inside blast furnaces is essential to ensure safe operation of the furnace and avoid accidents. However, traditional temperature monitoring methods rely on regular inspections, which makes it difficult to detect abnormal wall temperature increases in a timely manner, increasing the risk of damage to blast furnace equipment. Summary of the invention

[0003] In order to overcome the deficiencies of the prior art, the object of the present invention is to provide a method for timely detecting abnormal increase in wall temperature during operation of a blast furnace.

[0004] To achieve the above objectives, the present invention provides the following solutions:

[0005] A method for timely detecting abnormal increase in wall temperature during blast furnace operation, comprising:

[0006] Step 1: Obtain the temperature time series scatter plot of the target point of the blast furnace cooling wall;

[0007] Step 2: Determine the time period of normal temperature operation and the time period of abnormal temperature operation according to the fluctuation degree of the temperature time series scatter diagram in different time periods;

[0008] Step 3: Randomly select multiple temperature data from the normal temperature operation time period as statistical samples of the normal operation interval of the blast furnace;

[0009] Step 4: Randomly select multiple temperature data from the temperature abnormal operation time period as statistical samples of the blast furnace early warning interval;

[0010] Step 5: Determine the temperature warning upper limit value of the blast furnace cooling wall temperature operation according to the data distribution type of the blast furnace warning interval statistical sample;

[0011] Step 6: Determine whether the wall temperature is abnormal based on the temperature warning upper limit value of the blast furnace cooling wall temperature operation.

[0012] Preferably, in step 5, it includes:

[0013] When the data distribution type of the statistical samples of the blast furnace early warning interval is normal distribution, μ+3σ is used as the upper limit of the blast furnace cooling wall temperature warning; wherein μ represents the mean of the statistical samples of the blast furnace wall early warning interval, and σ represents the standard deviation of its normal distribution.

[0014] Preferably, in step 5, it also includes:

[0015] When the data distribution type of the blast furnace early warning interval statistical sample is non-normal and the data distribution type is right-skewed, the Box-Cox transformation is used to convert the data distribution type of the blast furnace early warning interval statistical sample into a normal distribution, and μ+3σ or μ-3σ is used as the temperature warning upper limit value of the blast furnace cooling wall temperature operation; where μ represents the mean of the blast furnace early warning interval statistical sample, and σ represents the standard deviation of the normal distribution.

[0016] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0017] The present invention provides a method for timely discovering abnormal increase in wall temperature during blast furnace operation. Compared with the prior art, the present invention is based on statistical principles and establishes alarm conditions by utilizing temperature fluctuations of the blast furnace cooling wall in different time periods. This can remind workers in real time to take corresponding measures in a timely manner, reduce the risk of equipment damage, and reduce the cost of blast furnace maintenance and shutdown. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] 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 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.

[0019] Figure 1 A scatter plot prepared in chronological order provided by the present invention;

[0020] Figure 2 A schematic diagram of the normality test results provided by the present invention;

[0021] Figure 3 This is the I-MR control diagram provided by the present invention. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 are within the scope of protection of the present invention.

[0023] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0024] The terms "first", "second", "third" and "fourth" in the specification and claims of the present application and the drawings are used to distinguish different objects rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a series of steps, processes, methods, etc. are not limited to the listed steps, but may optionally include steps that are not listed, or may optionally include other step elements inherent to these processes, methods, products or devices.

[0025] In order to make the above-mentioned objectives, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0026] See also Figure 1-3 , a method for timely detecting abnormal increase in wall temperature during blast furnace operation, comprising:

[0027] Step 1: Obtain the temperature time series scatter plot of the target point of the blast furnace cooling wall;

[0028] Step 2: Determine the time period of normal temperature operation and the time period of abnormal temperature operation according to the fluctuation degree of the temperature time series scatter diagram in different time periods;

[0029] Step 3: Randomly select multiple temperature data from the time period during the normal temperature operation as statistical samples of the normal operation interval of the blast furnace;

[0030] Step 4: Randomly select multiple temperature data from the time period during the abnormal temperature operation as statistical samples of the blast furnace early warning interval;

[0031] Step 5: Determine the upper limit value of the blast furnace cooling wall temperature warning according to the data distribution type of the blast furnace warning interval statistical sample;

[0032] Furthermore, in step 5, it includes:

[0033] When the data distribution type of the statistical sample in the normal operation interval of the blast furnace is a normal distribution, μ+3σ is used as the temperature warning upper limit value of the blast furnace cooling wall temperature operation; wherein μ represents the mean of the statistical sample in the normal operation interval of the blast furnace, and σ represents the standard deviation of the normal distribution.

[0034] When the data distribution type of the statistical samples in the normal operation interval of the blast furnace is non-normal and the data distribution type is right-skewed, the Box-Cox transformation is used to convert the data distribution type of the statistical samples in the normal operation interval of the blast furnace into a normal distribution, and μ±3σ or μ-3σ is used as the temperature warning upper limit value of the blast furnace cooling wall temperature operation; where μ represents the mean of the statistical samples in the blast furnace warning interval, and σ represents the standard deviation of the normal distribution.

[0035] Step 6: When the temperature of the target point exceeds the upper limit, an abnormal alarm is issued; further, when the temperature point monitoring values ​​are located on the higher temperature side outside the mean for 9 consecutive points, an abnormal alarm is issued; when the temperature point monitoring values ​​increase or decrease for 6 consecutive points, an abnormal alarm is issued (the lower the data after the Box-cox transformation, the higher the temperature before the transformation, so the gradual decrease of some transformed data indicates that the wall monitoring value before the transformation is gradually increasing, so in this case, an alarm is also required if the transformed monitoring value decreases for 6 consecutive points).

[0036] The present invention is based on statistical principles and establishes alarm conditions by utilizing the temperature fluctuations of the blast furnace cooling wall in different time periods, which can remind workers in real time to take corresponding measures in time, reduce the risk of equipment damage, and reduce the cost of blast furnace maintenance and shutdown.

[0037] The present invention further describes the method for timely detecting abnormal increase in wall temperature during blast furnace operation in combination with specific embodiments below:

[0038] 1. Make a scatter plot based on the time series to determine the time periods of normal operation and abnormal operation of the temperature at that point on the wall: the wall temperature distribution is compact, and the mean and median are low, which is the normal operation range of the normal lining; the temperature fluctuates greatly, the temperature high points increase, the temperature diverges, the distribution is wide, and the temperature mean and median are significantly higher than the previous period, which is the abnormal operation range after the lining is damaged.

[0039] 2. Use the wall temperature monitoring system to collect statistics on the hourly average temperature data of a certain point on the wall in the stable working range of the wall, and randomly select 100 groups of data as statistical samples of the normal operating range; randomly select 100 groups of data in the abnormal operating range as statistical samples of the abnormal operating range.

[0040] 3. Compare 100 randomly selected data points of the wall temperature data during the two operation periods to determine whether there is a significant change in temperature between the two periods. If the test shows that the wall temperature has increased significantly, it means that the wall temperature in the interval where the temperature fluctuation increases significantly is significantly higher than that in the previous normal operation interval. The abnormal operation stage with large temperature fluctuation is taken as the warning area.

[0041] 4. If the data during the wall warning period is normally distributed, the mean wall temperature μ+3σ (σ is the standard deviation of this normal distribution) is used as the upper limit of the temperature warning for normal operation. Under normal operation, the probability that the wall temperature exceeds this upper limit is less than 1%. If the wall at this point exceeds this upper limit, on-site confirmation is required. If it exceeds this value for 2 consecutive hours, even if the furnace shell does not turn red, measures such as enhanced cooling or reduced smelting intensity must be taken. It should be noted that when the temperature point monitoring value is located on the higher side of the value outside the mean μ for 9 consecutive points, an abnormal alarm is issued even if it does not exceed μ+3σ; when the temperature point monitoring value increases for 6 consecutive points, it indicates that the temperature monitoring value at this point has increased for 6 consecutive hours, and an abnormal alarm is issued.

[0042] 5. If the data during the wall warning period is non-normal and the data is right-skewed, it means that the wall temperature is significantly affected by the slag shedding, and a large amount of data with abnormally high temperature is collected. At this time, the data needs to be Box-Cox transformed. The Box-Cox method converts non-normal data to normal data through various transformation types. Table 1 shows some common transformations, where Y' is the transformation of data Y.

[0043] 6. The data after Box-Cox transformation is normally distributed. The transformed normal data is based on the mean μ++3σ or μ-3σ as the upper limit of the temperature warning for normal operation (σ is the standard deviation of the normal distribution after transformation); when λ is a positive number, it is judged according to Instructions 4. When λ is a negative number, the upper limit of the wall temperature warning is μ-3σ. When the temperature point monitoring value is located on the lower side of the value other than the mean μ for 9 consecutive points, an abnormal alarm is issued even if it does not exceed μ-3σ; when the temperature point monitoring value after transformation decreases for 6 consecutive points, it indicates that the temperature monitoring value of the point before transformation has increased for 6 consecutive hours, and an abnormal alarm is issued.

[0044] Table 1

[0045]

[0046]

[0047] The present invention is combined with the accompanying drawings to describe a 4000m 3 The construction process of the abnormal upper limit value of the wall temperature of the first-class blast furnace is further explained:

[0048] 1. Create a scatter plot of the temperature monitoring data of a certain point on the wall in chronological order.

[0049] from Figure 1It can be seen that the temperature at this point has the characteristics of small temperature fluctuation, compact temperature distribution, and low maximum value in the early stage, and large temperature fluctuation, loose distribution, and high maximum temperature value in the later stage, indicating that the internal furnace lining has been seriously damaged. Therefore, 100 data points are randomly selected in the area with small temperature fluctuation as sample points during the stable operation of the wall. 100 data points are randomly selected in the time zone with large fluctuation in the later stage as sample points in the early warning area.

[0050] 2. Normality test

[0051] like Figure 2 As shown, the normality test of the above two samples was performed and it was found that both were non-normally distributed (P value < 0.005).

[0052] 3. Identify the distribution of samples, as shown in Table 2.

[0053] Table 2

[0054] distributed AD P Maximum Likelihood Ratio P Normal 8.945 <0.005 Box-Cox transformation 0.645 0.090 Logistic 5.737 <0.005 Log-Logistic 3.046 <0.005 3-parameter log-logistic 0.122 * 0.000

[0055] After Box-Cox transformation (Box-Cox transformation parameter λ=-2), the data showed normality (P value>0.05).

[0056] 4. Calculate the warning limit

[0057] The data points of the later period with large fluctuations were transformed by Box-Cox and descriptive statistics were obtained. The mean of the transformed samples was 0.000410 and the standard deviation was 0.000185. Since the transformation parameter λ of Box-Cox is -2, the transformed value is 1 / the original value 2 (the higher the actual wall temperature, the smaller the transformed value).

[0058] 5. Perform Box-Cox conversion on the wall operating temperature and continuously plot points to form a control chart.

[0059] The control chart of the temperature points after Box-Cox transformation is as follows Figure 3 As shown, it can be seen that the wall temperature has been below the mean for 7 consecutive hours since 37 o'clock, and this situation continues at many points after 37 o'clock (indicating that the wall temperature is continuously higher than the mean before the conversion, indicating that the wall temperature is continuously high before the Box-Cox transformation). According to the normal distribution probability density function, the probability of this situation is less than 1% (the case of the red point number 2), so this situation is a continuous high wall temperature. On-site verification is required. The data alarm time is 5 hours earlier than the time when the furnace skin is manually discovered and reported to be red, which shows the timeliness and accuracy of this method.

[0060] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the method disclosed in the embodiment, since it corresponds to the device disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the device part description.

[0061] The principles and implementation methods of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A method for timely detecting abnormal increase in wall temperature during blast furnace operation, characterized in that: include: Step 1: Obtain the temperature time series scatter plot of the target point of the blast furnace cooling wall; Step 2: Determine the normal temperature operation time period and the abnormal temperature operation time period according to the fluctuation degree of the temperature time series scatter diagram in different time periods; Step 3: Randomly select multiple temperature data from the normal temperature operation time period as statistical samples of the normal operation interval of the blast furnace; Step 4: Randomly select multiple temperature data from the temperature abnormal operation time period as statistical samples of the blast furnace early warning interval; Step 5: Determine the temperature warning upper limit value of the blast furnace cooling wall temperature operation according to the data distribution type of the blast furnace warning interval statistical sample; Step 6: Determine whether the wall temperature is abnormal based on the temperature warning upper limit value of the blast furnace cooling wall temperature operation.

2. A method for timely detecting abnormal increase in wall temperature during blast furnace operation as claimed in claim 1, characterized in that: In step 5, it includes: When the data distribution type of the statistical sample of the blast furnace early warning interval is normal distribution, μ+3σ is used as the temperature warning upper limit value of the blast furnace cooling wall temperature operation; wherein μ represents the mean of the statistical sample of the blast furnace early warning interval, and σ represents the standard deviation of the normal distribution.

3. A method for timely detecting abnormal increase in wall temperature during blast furnace operation as claimed in claim 2, characterized in that: In the step 5, it also includes: When the data distribution type of the blast furnace early warning interval statistical sample is non-normal and the data distribution type is right-skewed, the Box-Cox transformation is used to convert the data distribution type of the blast furnace early warning interval statistical sample into a normal distribution, and μ±3σ or μ-3σ is used as the temperature warning upper limit value of the blast furnace cooling wall temperature operation; where μ represents the mean of the blast furnace early warning interval statistical sample, and σ represents the standard deviation of the normal distribution.

4. A method for timely detecting abnormal increase in wall temperature during blast furnace operation as claimed in claim 2, characterized in that: When the data distribution type of the blast furnace early warning interval statistical sample is normal distribution, when the temperature point monitoring value exceeds the blast furnace early warning interval statistical sample mean μ for 9 consecutive points, an abnormal alarm is issued; when the temperature point monitoring value increases for 6 consecutive points, an abnormal alarm is issued; when the temperature point monitoring value exceeds the temperature warning upper limit value of the blast furnace cooling wall temperature operation, an abnormal alarm is issued.

5. A method for timely detecting abnormal increase in wall temperature during blast furnace operation as claimed in claim 3, characterized in that: When the data distribution type of the blast furnace early warning interval statistical sample is non-normal distribution, when the temperature point monitoring value is lower than the blast furnace early warning interval statistical sample mean μ for 9 consecutive points, an abnormal alarm is issued; when the temperature point monitoring value decreases for 6 consecutive points, an abnormal alarm is issued; when the temperature point monitoring value exceeds the temperature warning upper limit value of the blast furnace cooling wall temperature operation, an abnormal alarm is issued.

Images