Blast furnace abnormality determination device, blast furnace abnormality determination method, blast furnace operation method, blast furnace operation system, blast furnace abnormality determination server device, program for blast furnace abnormality determination server device, and display terminal device

Abstract

This blast furnace abnormality determination device comprises: a sensor signal acquisition means for acquiring measurement data of a plurality of sensors installed at different positions in a blast furnace; an evaluation index calculation means for calculating a unified evaluation index indicating a furnace condition state from the measurement data acquired by the sensor signal acquisition means; an evaluation index difference value calculation means for calculating an evaluation index difference value, which is the absolute value of the time difference of evaluation indices calculated by the evaluation index calculation means; and a determination means for determining an abnormality of the blast furnace on the basis of the evaluation index difference value calculated by the evaluation index difference value calculation means, and outputting the determined results and the data used in the determination.

Description

Technical Field

[0001] The present invention relates to a blast furnace abnormality determination device, a blast furnace abnormality determination method, a blast furnace operation method, a blast furnace operation system, a blast furnace abnormality determination server device, a program for the blast furnace abnormality determination server device, and a display terminal device.

Background Art

[0002] In a plant, various abnormalities may occur. Detecting abnormalities early and dealing with them appropriately are important for preventing the occurrence of serious abnormalities and troubles. For example, under the current low coke ratio operation of blast furnaces, it is important to accurately and more quickly detect or estimate the furnace condition of the blast furnace, particularly the ventilation state of the blast furnace and its changes, and to always maintain the ventilation state of the blast furnace in good condition. Conventionally, as a ventilation index representing the ventilation state of the blast furnace, the ventilation resistance calculated from the difference value between the top pressure and the blowing pressure is used. And for ventilation indices such as ventilation resistance, a threshold value for determining ventilation deterioration is set, and when the ventilation index exceeds the threshold value, it is determined that ventilation has deteriorated. Further, Patent Document 1 describes a method of performing abnormality determination of a blast furnace by calculating an evaluation index using a statistical method such as principal component analysis with the shaft pressure as an input. The method described in Patent Document 1 calculates, as an evaluation index, the ratio between the Q statistic calculated based on the data of the stability limit and the Q statistic calculated based on the operation data of the abnormality detection target, and sets a threshold value for the evaluation index to perform abnormality determination of the blast furnace.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] When the abnormality determination of the blast furnace is performed using the method described in Patent Document 1, when a certain shaft pressure deviation continuously occurs at the same stage (the same height position) of the blast furnace, the evaluation index continuously increases, and the evaluation index may continuously exceed the threshold value. This state often occurs when the pressure deviation continuously occurs at a specific position. Although this state can be regarded as slightly abnormal, there are cases where it is determined that no countermeasures are necessary, and it is not desirable to continuously determine it as abnormal. Especially in a blast furnace with a large furnace volume, even if a slight pressure deviation occurs, the impact on the operation is small, so the operation often continues as it is, and sometimes a slight pressure deviation is not regarded as abnormal. For example, in the example shown in FIG. 7, a large temporal variation occurs in the shaft pressure in the first half, and a steady deviation occurs at the same stage of the shaft pressure in the second half. In this case, since the level sense of the evaluation index (Q statistic) calculated based on the shaft pressure is the same in the first half and the second half, it is impossible to distinguish between the large temporal variation of the shaft pressure and the steady deviation and perform an abnormality determination. Also, when an abnormal state occurs in which the short-time temporal variation of the shaft pressure becomes large while the deviation of the shaft pressure continuously occurs within a predetermined range, since the evaluation index already exceeds the threshold value, it is impossible to perform an abnormality determination of the short-time temporal variation.

[0005] The present invention has been made to solve the above problems, and an object thereof is to provide an abnormality determination device and an abnormality determination method for a blast furnace capable of accurately determining an abnormality of the blast furnace. Another object of the present invention is to provide an operation method for a blast furnace capable of stably operating the blast furnace, an operation system for a blast furnace, an abnormality determination server device for a blast furnace, a program for the abnormality determination server device for a blast furnace, and a display terminal device.

Means for Solving the Problems

[0006] The blast furnace abnormality determination device according to the first aspect of the present invention includes: a sensor signal acquisition means for acquiring measurement data of a plurality of sensors installed at different positions of the blast furnace; an evaluation index calculation means for calculating a unified evaluation index indicating the furnace condition of the blast furnace from the measurement data acquired by the sensor signal acquisition means; an evaluation index difference value calculation means for calculating an evaluation index difference value which is the absolute value of the time difference of the evaluation index calculated by the evaluation index calculation means; and a determination means for determining an abnormality of the blast furnace based on the evaluation index difference value calculated by the evaluation index difference value calculation means, and outputting the determined result and the data used for the determination.

[0007] The blast furnace abnormality determination device according to the second aspect of the present invention includes: a sensor signal acquisition means for acquiring measurement data of a plurality of sensors installed at different positions of the blast furnace; an evaluation index calculation means for calculating a unified evaluation index indicating the furnace condition of the blast furnace from the measurement data acquired by the sensor signal acquisition means; an evaluation index difference value calculation means for calculating an evaluation index difference value which is the absolute value of the time difference of the evaluation index calculated by the evaluation index calculation means; an evaluation index difference integrated value calculation means for calculating an evaluation index difference integrated value which is the integrated value of the evaluation index difference value within a predetermined time range calculated by the evaluation index difference value calculation means; and a determination means for determining an abnormality of the blast furnace based on the evaluation index difference integrated value calculated by the evaluation index difference integrated value calculation means, and outputting the determined result and the data used for the determination.

[0008] The evaluation index calculation means may calculate the evaluation index using a statistical learning model that outputs an evaluation index obtained by standardizing the furnace condition of the blast furnace based on the measurement data of the sensors in the normal state of the blast furnace.

[0009] The method for determining abnormality of a blast furnace according to the first aspect of the present invention includes a sensor signal acquisition step of acquiring measurement data of a plurality of sensors installed at different positions of the blast furnace, an evaluation index calculation step of calculating a unified evaluation index indicating the furnace condition of the blast furnace from the measurement data acquired in the sensor signal acquisition step, an evaluation index difference value calculation step of calculating an evaluation index difference value which is the absolute value of the time difference of the evaluation index calculated in the evaluation index calculation step, and a determination step of determining the abnormality of the blast furnace based on the evaluation index difference value calculated in the evaluation index difference value calculation step and outputting the determined result and the data used for the determination.

[0010] The method for determining abnormality of a blast furnace according to the second aspect of the present invention includes a sensor signal acquisition step of acquiring measurement data of a plurality of sensors installed at different positions of the blast furnace, an evaluation index calculation step of calculating a unified evaluation index indicating the furnace condition of the blast furnace from the measurement data acquired in the sensor signal acquisition step, an evaluation index difference value calculation step of calculating an evaluation index difference value which is the absolute value of the time difference of the evaluation index calculated in the evaluation index calculation step, an evaluation index difference integrated value calculation step of calculating an evaluation index difference integrated value which is the integrated value of the evaluation index difference value in a predetermined time range calculated in the evaluation index difference value calculation step, and a determination step of determining the abnormality of the blast furnace based on the evaluation index difference integrated value calculated in the evaluation index difference integrated value calculation step and outputting the determined result and the data used for the determination.

[0011] The evaluation index calculation step preferably includes a step of calculating the evaluation index using a statistical learning model that outputs an evaluation index obtained by standardizing the furnace condition of the blast furnace based on the measurement data of the sensors in the normal state of the blast furnace.

[0012] The operation method of the blast furnace according to the present invention operates the blast furnace while determining whether the blast furnace is in an abnormal state using the method for determining abnormality of the blast furnace according to the present invention.

[0013] The blast furnace operation system according to the first aspect of the present invention includes an abnormality determination device for a blast furnace that determines an abnormality of the blast furnace, and a display device that is connected to the abnormality determination device of the blast furnace via a network and displays information output from the abnormality determination device of the blast furnace. The abnormality determination device for the blast furnace includes a sensor signal acquisition means for acquiring measurement data of a plurality of sensors installed at different positions of the blast furnace, an evaluation index calculation means for calculating a unified evaluation index indicating the furnace condition of the blast furnace from the measurement data acquired by the sensor signal acquisition means, an evaluation index difference value calculation means for calculating an evaluation index difference value that is the absolute value of the time difference of the evaluation index calculated by the evaluation index calculation means, and a determination means for determining an abnormality of the blast furnace based on the evaluation index difference value calculated by the evaluation index difference value calculation means and outputting the determined result and the data used for the determination.

[0014] The blast furnace operation system according to the second aspect of the present invention includes an abnormality determination device for a blast furnace that determines an abnormality of the blast furnace, and a display device that is connected to the abnormality determination device of the blast furnace via a network and displays information output from the abnormality determination device of the blast furnace. The abnormality determination device for the blast furnace includes a sensor signal acquisition means for acquiring measurement data of a plurality of sensors installed at different positions of the blast furnace, an evaluation index calculation means for calculating a unified evaluation index indicating the furnace condition of the blast furnace from the measurement data acquired by the sensor signal acquisition means, an evaluation index difference value calculation means for calculating an evaluation index difference value that is the absolute value of the time difference of the evaluation index calculated by the evaluation index calculation means, an evaluation index difference integrated value calculation means for calculating an evaluation index difference integrated value that is the integrated value of the evaluation index difference value within a predetermined time range calculated by the evaluation index difference value calculation means, and a determination means for determining an abnormality of the blast furnace based on the evaluation index difference integrated value calculated by the evaluation index difference integrated value calculation means and outputting the determined result and the data used for the determination.

[0015] The blast furnace abnormality determination server device according to the first aspect of the present invention is a blast furnace abnormality determination server device that constructs an operation system of a blast furnace together with a data collection device that acquires and stores measurement data from sensors installed in the blast furnace, and a display terminal device that acquires and displays abnormality determination information from the blast furnace abnormality determination server device, and includes: a sensor signal acquisition means for acquiring measurement data of a plurality of sensors installed at different positions of the blast furnace from the data collection device; an evaluation index calculation means for calculating a unified evaluation index indicating the furnace condition state of the blast furnace from the measurement data acquired by the sensor signal acquisition means; an evaluation index difference value calculation means for calculating an evaluation index difference value that is the absolute value of the time difference of the evaluation index calculated by the evaluation index calculation means; a determination means for determining an abnormality of the blast furnace based on the evaluation index difference value calculated by the evaluation index difference value calculation means, and outputting the determined result and the data used for the determination; and a determination data transmission means for transmitting abnormality determination information including the determined result and the data used for the determination.

[0016] The blast furnace abnormality determination server device according to the second aspect of the present invention is a blast furnace abnormality determination server device that constructs an operation system of a blast furnace together with a data collection device that acquires and stores measurement data from sensors installed in the blast furnace, and a display terminal device that acquires and displays abnormality determination information from the blast furnace abnormality determination server device, and includes: a sensor signal acquisition means for acquiring measurement data of a plurality of sensors installed at different positions of the blast furnace from the data collection device; an evaluation index calculation means for calculating a unified evaluation index indicating the furnace condition state of the blast furnace from the measurement data acquired by the sensor signal acquisition means; an evaluation index difference value calculation means for calculating an evaluation index difference value that is the absolute value of the time difference of the evaluation index calculated by the evaluation index calculation means; an evaluation index difference integrated value calculation means for calculating an evaluation index difference integrated value that is an integrated value of the evaluation index difference value within a predetermined time range calculated by the evaluation index difference value calculation means; a determination means for determining an abnormality of the blast furnace based on the evaluation index difference integrated value calculated by the evaluation index difference integrated value calculation means, and outputting the determined result and the data used for the determination; and a determination data transmission means for transmitting abnormality determination information including the determined result and the data used for the determination.

[0017] The program of the abnormal determination server device for a blast furnace according to the first aspect of the present invention is a program of an abnormal determination server device for a blast furnace that constructs an operation system for a blast furnace together with a data collection device that acquires and accumulates measurement data from sensors installed in the blast furnace, and a display terminal device that acquires and displays abnormal determination information from the abnormal determination server device for the blast furnace. The computer is caused to function as sensor signal acquisition means for acquiring measurement data of a plurality of sensors installed at different positions in the blast furnace from the data collection device, evaluation index calculation means for calculating a unified evaluation index indicating the furnace condition state of the blast furnace from the measurement data acquired by the sensor signal acquisition means, evaluation index difference value calculation means for calculating an evaluation index difference value that is the absolute value of the time difference of the evaluation index calculated by the evaluation index calculation means, determination means for determining an abnormality in the blast furnace based on the evaluation index difference value calculated by the evaluation index difference value calculation means, and outputting the determined result and the data used for the determination, and determination data transmission means for transmitting abnormal determination information including the determined result and the data used for the determination.

[0018] The program of the abnormal condition determination server device for a blast furnace according to the second aspect of the present invention is a program of an abnormal condition determination server device for a blast furnace that constructs an operation system of a blast furnace together with a data collection device that acquires and accumulates measurement data from sensors installed in the blast furnace, and a display terminal device that acquires and displays abnormal condition determination information from the abnormal condition determination server device for the blast furnace. The program causes a computer to function as: a sensor signal acquisition means for acquiring measurement data from a plurality of sensors installed at different positions in the blast furnace from the data collection device; an evaluation index calculation means for calculating a unified evaluation index indicating the furnace condition of the blast furnace from the measurement data acquired by the sensor signal acquisition means; an evaluation index difference value calculation means for calculating an evaluation index difference value that is the absolute value of the time difference of the evaluation index calculated by the evaluation index calculation means; an evaluation index difference integrated value calculation means for calculating an evaluation index difference integrated value that is the integrated value of the evaluation index difference value within a predetermined time range calculated by the evaluation index difference value calculation means; a determination means for determining an abnormality in the blast furnace based on the evaluation index difference integrated value calculated by the evaluation index difference integrated value calculation means, and outputting the determined result and the data used for the determination; and a determination data transmission means for transmitting abnormality determination information including the determined result and the data used for the determination.

[0019] The display terminal device according to the first aspect of the present invention includes a data collection device that acquires and stores measurement data from sensors installed in a blast furnace, sensor signal acquisition means that acquires measurement data of a plurality of sensors installed at different positions of the blast furnace from the data collection device, evaluation index calculation means that calculates a unified evaluation index indicating the furnace condition of the blast furnace from the measurement data acquired by the sensor signal acquisition means, evaluation index difference value calculation means that calculates an evaluation index difference value that is the absolute value of the time difference of the evaluation index calculated by the evaluation index calculation means, determination means that determines an abnormality in the blast furnace based on the evaluation index difference value calculated by the evaluation index difference value calculation means and outputs the determination result and the data used for the determination, and determination data transmission means that transmits abnormality determination information including the determination result and the data used for the determination. It is a display terminal device that constructs an operation system for a blast furnace together with an abnormality determination server device for a blast furnace, and acquires and displays the abnormality determination information from the abnormality determination server device for the blast furnace via a network.

[0020] The display terminal device according to the second aspect of the present invention includes a data collection device that acquires and stores measurement data from sensors installed in a blast furnace, sensor signal acquisition means that acquires measurement data of a plurality of sensors installed at different positions of the blast furnace from the data collection device, evaluation index calculation means that calculates a unified evaluation index indicating the furnace condition of the blast furnace from the measurement data acquired by the sensor signal acquisition means, evaluation index difference value calculation means that calculates an evaluation index difference value that is the absolute value of the time difference of the evaluation index calculated by the evaluation index calculation means, evaluation index difference integrated value calculation means that calculates an evaluation index difference integrated value that is the integrated value of the evaluation index difference value within a predetermined time range calculated by the evaluation index difference value calculation means, determination means that determines an abnormality in the blast furnace based on the evaluation index difference integrated value calculated by the evaluation index difference integrated value calculation means and outputs the determination result and the data used for the determination, and determination data transmission means that transmits abnormality determination information including the determination result and the data used for the determination. It is a display terminal device that constructs an operation system for a blast furnace together with an abnormality determination server device for a blast furnace, and acquires and displays the abnormality determination information from the abnormality determination server device for the blast furnace via a network.

Advantages of the Invention

[0021] According to the blast furnace abnormality determination device and the abnormality determination method of the present invention, the abnormality of the blast furnace can be accurately determined. Further, according to the blast furnace operation method, the blast furnace operation system, the blast furnace abnormality determination server device, the program of the blast furnace abnormality determination server device, and the display terminal device of the present invention, the blast furnace can be stably operated.

Brief Description of the Drawings

[0022]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Modes for Carrying Out the Invention

[0023] Hereinafter, a blast furnace abnormality determination device according to an embodiment of the present invention will be described.

[0024] FIG. 1 is a block diagram showing the configuration of a blast furnace abnormality determination device according to an embodiment of the present invention. As shown in FIG. 1, a blast furnace abnormality determination device 1 according to an embodiment of the present invention is composed of an information processing device such as a general-purpose personal computer or a dedicated computer. The blast furnace abnormality determination device 1 functions as a sensor signal acquisition means 11, an evaluation index calculation means 12, an evaluation index difference value calculation means 13, a determination means 14, and a determination data transmission means 15 when an arithmetic processing device inside the information processing device executes a computer program.

[0025] The sensor signal acquisition means 11 acquires various data indicating the furnace condition of the blast furnace detected by the sensors 22 stored in the data collection device 21. The data collection device 21 is composed of a storage device such as a database. Further, the sensors 22 are installed at a plurality of different positions of the blast furnace and detect various data indicating the furnace condition of the blast furnace. Examples of the sensors 22 include a group of pressure sensors that detect the shaft pressure of the blast furnace. In this case, the group of pressure sensors is installed at a plurality of locations in the height direction and the circumferential direction of the blast furnace. Although the installation method and the number of installed pressure sensors vary depending on the blast furnace, the circumferential direction is often installed at about 4 to 8 points at substantially equal intervals, and the height direction is often installed at about 6 to 12 points from the lower part of the furnace to near the upper surface of the raw materials.

[0026] The evaluation index calculation means 12 calculates an evaluation index regarding the furnace condition of the blast furnace using various data indicating the furnace condition of the blast furnace acquired by the sensor signal acquisition means 11. The calculation method of the evaluation index is not particularly limited, and any method may be used as long as it unifies a plurality of data indicating the furnace condition of the blast furnace and converts it into an evaluation index. The evaluation index calculation means 12 may calculate the evaluation index of the blast furnace using, for example, the method described in Patent Document 1. Further, the evaluation index calculation means 12 may, for example, divide the evaluation index calculated from the data group used as the stability limit value by the evaluation index calculated from the data to be determined, and perform processing (standardization) such that the evaluation index becomes 1 at the stability limit, that is, standardize the evaluation index. Alternatively, as another method, an autoencoder using a neural network can also be presented as an example of using a neural network. The evaluation index calculation means 12 evaluates the magnitude of the difference signal between the output of the autoencoder learned from the normal data and the input data (it may be evaluated as a vector for a plurality of signals), and after determining the stability limit value, calculates the evaluation index during operation in the same manner as described above.

[0027] In this embodiment, an example in which the Q statistic is used as the evaluation index is shown. The Q statistic is calculated by principal component analysis. Principal component analysis is a mathematical process that replaces (dimensionality reduction) a plurality of (multiple dimensions) data groups that are synchronized with a small number of variables that well reflect the characteristics of the original data while minimizing the loss of information amount of the original data group. In the case of the data of the shaft pressure of the blast furnace, although a large number of pressure sensors are installed for one blast furnace as described above, here it is assumed that 30 points are installed. Therefore, if the principal component analysis is applied and replaced with several variables (principal component values) that well reflect the characteristics of the 30-point data group, the furnace condition of the blast furnace can be easily estimated by monitoring the small number of variables generated by the principal component analysis without observing all of the 30-point data group. However, in this embodiment, the Q statistic is used as the evaluation index, but evaluation index standardization by independent component analysis or evaluation index standardization using a machine learning method may also be used.

[0028] In the data of the shaft pressure of the blast furnace, in the first principal component value with the largest variance in the principal component analysis, the component of the synchronized movement of each shaft pressure during the stable operation of the blast furnace appears. On the other hand, after the second component value of the principal component analysis, components other than the stable period appear, and in this device, these components are used for anomaly detection. Synchronization means that the behavior of the operating variables has coordination with the time progression or operating actions in the process. In this embodiment, principal component analysis is applied to the data of sensor 2 at each time, and the second principal component value with the largest variance value is calculated in the component where the asynchrony appears, and this value is used as the Q statistic. However, if an abnormal phenomenon appears significantly in the third component value and subsequent values, those values can also be used.

[0029] Also, in this embodiment, first, in a normal operating section that is not considered abnormal, principal component analysis is applied to the time-series data of the data of sensor 2, and the time-series data of the second principal component is created. In this normal operating section that is not considered abnormal, it is necessary to include data within the stability limit, that is, the limit that can be judged as normal. Next, the maximum value of the time-series data of the second principal component is obtained. Obtaining the maximum value of the second principal component in a normal time interval means obtaining the maximum value of the fluctuation range of the data of sensor 2 when normal operation is being carried out and the deviation amount from the normal operating range, that is, the value of the stability limit. Then, when detecting an operating anomaly in the blast furnace, the second principal component calculated from the data of sensor 2 in the operating range where an anomaly is occurring is divided by the maximum value of the second principal component calculated from the data of sensor 2 in the normal operating range, and the index is used as an evaluation index to detect anomalies in the blast furnace.

[0030] In this embodiment, as described above, a calculation formula for calculating the second principal component is defined using the result of the principal component analysis performed based on the data acquired during normal operation. Further, an evaluation index calculation model for calculating a unified evaluation index indicating the furnace condition of the blast furnace from a plurality of measurement data is constructed in advance using the calculation formula for calculating the second principal component and the maximum value of the second principal component, and the evaluation index is calculated. The construction of the evaluation index calculation model used for the calculation of the evaluation index may be carried out using a computer such as an analysis personal computer based on the data stored in the data collection device 21. Alternatively, as shown in FIG. 2, an analysis tool may be installed in the abnormal determination device 1 of the blast furnace, and the evaluation index calculation model construction means 16 may be provided for implementation.

[0031] Return to FIG. 1. The evaluation index difference value calculation means 13 calculates the absolute value of the change amount (evaluation index time difference value) in the first predetermined time range for the evaluation index calculated by the evaluation index calculation means 12. The first predetermined time is set in advance using the actual value of the absolute value at the time of abnormal occurrence and the like. Then, the evaluation index difference value calculation means 13 outputs the absolute value of the calculated evaluation index time difference value to the determination means 14.

[0032] The determination means 14 determines whether or not an abnormality has occurred in the blast furnace by determining whether or not the absolute value of the evaluation index time difference value output from the evaluation index difference value calculation means 13 is, for example, equal to or greater than a first predetermined threshold value. Then, the determination means 14 outputs information indicating the determination result and related data (sensor data, evaluation index value, absolute value of the evaluation index time difference value, etc.) serving as the basis for the determination.

[0033] The determination data transmission means 15 transmits the abnormality determination information including the result determined by the determination means 14 and the data used for the determination to the evaluation result display device 23. The evaluation result display device 23 is composed of a display device such as a liquid crystal display, and acquires and displays the abnormality determination information transmitted from the determination data transmission means 15. When information indicating that an abnormality has occurred in the blast furnace is displayed on the evaluation result display device 23, the operator takes measures such as reducing the blast. By connecting the blast furnace abnormality determination device 1 and the evaluation result display device 3 via a network, a client-server type system in which the evaluation result display device 23 acquires and displays the information transmitted from the determination data transmission means 15 via the network may be constructed. Examples of the network include a telecommunication line such as the Internet, a telephone communication network such as a mobile phone, and a wireless communication network such as WiFi (registered trademark). In this case, the blast furnace abnormality determination device 1 of the present invention functions as a blast furnace abnormality determination server device according to the present invention, and the evaluation result display device 23 functions as a display terminal device according to the present invention.

[0034] Thereby, when the steady deviation of the shaft pressure is not regarded as a major operation deterioration, the influence of the steady deviation of the shaft pressure can be reduced, and short-time temporal variations that would be buried and affected by the steady deviation can be accurately detected. Then, the abnormality of the blast furnace can be accurately detected at an early stage without requiring much labor, and the blast furnace can be stably operated.

[0035] 〔Modification Example〕 FIG. 3 is a block diagram showing the configuration of a modification example of the blast furnace abnormality determination device 1 shown in FIG. 1. The blast furnace abnormality determination device 1 shown in FIG. 3 has a configuration in which an evaluation index difference integrated value calculation means 17 is added to the blast furnace abnormality determination device 1 shown in FIG. 1. The functions of the sensor signal acquisition means 11, the evaluation index calculation means 12, and the evaluation index difference value calculation means 13 shown in FIG. 3 are the same as the functions of the sensor signal acquisition means 11, the evaluation index calculation means 12, and the evaluation index difference value calculation means 13 shown in FIG. 1. Hereinafter, the functions of the evaluation index difference integrated value calculation means 17, the determination means 14, the determination data transmission means 15, and the evaluation result display device 23 will be described.

[0036] The evaluation index difference integrated value calculation means 17 calculates the integrated value of the absolute value of the evaluation index time difference value calculated by the evaluation index difference value calculation means 13 within a second predetermined time range. The second predetermined time is preset using the actual value of the integrated value at the time of abnormality occurrence and the like. Then, the evaluation index difference integrated value calculation means 17 outputs the calculated integrated value to the determination means 14.

[0037] The determination means 14 determines whether an abnormality has occurred in the blast furnace by determining whether the integrated value output from the evaluation index difference integrated value calculation means 17 is, for example, equal to or greater than a second predetermined threshold value. Then, the determination means 14 outputs information indicating the determination result and related data serving as the basis for the determination (sensor data, evaluation index value, absolute value of the evaluation index time difference value, absolute value integrated value of the evaluation index time difference value, etc.). The determination data transmission means 15 transmits abnormality determination information including the result determined by the determination means 14 and the data used for the determination to the evaluation result display device 23.

[0038] The evaluation result display device 23 is composed of a display device such as a liquid crystal display, and acquires and displays the information transmitted from the determination data transmission means 15. When information indicating that an abnormality has occurred in the blast furnace is displayed on the evaluation result display device 8, the operator takes measures such as reducing the blast. As a result, when the steady deviation of the shaft pressure is not regarded as a major operation deterioration, the influence of the steady deviation of the shaft pressure is reduced, and short-time temporal variations that would otherwise be buried under the influence of the steady deviation are accurately detected. In addition, the abnormality detection accuracy when the short-time variations continue is improved. Therefore, the abnormality of the blast furnace can be accurately detected at an early stage without requiring much labor, and the blast furnace can be operated stably. By connecting the blast furnace abnormality determination device 1 and the evaluation result display device 3 via a network, a client-server type system can be constructed in which the evaluation result display device 23 acquires and displays the information transmitted from the determination data transmission means 15 via the network. Examples of the network include a telecommunication line such as the Internet, a telephone communication network such as a mobile phone, and a wireless communication network such as WiFi (registered trademark). In this case, the blast furnace abnormality determination device 1 functions as the blast furnace abnormality determination server device according to the present invention, and the evaluation result display device 23 functions as the display terminal device according to the present invention.

Example

[0039] In this embodiment, as shown in FIG. 4, shaft pressure gauges are arranged in three stages (stage A, stage B, and stage C from top to bottom) in the vertical direction of the furnace body, and four shaft pressure gauges are arranged at equal intervals in the circumferential direction at each stage. First, the evaluation index difference value calculation means 13 determines whether an abnormality has occurred in the blast furnace. The determination result is shown in FIG. 5. In the example shown in FIG. 5, the absolute value of the time difference value of the evaluation index was calculated with the first predetermined time being 5 minutes. This first predetermined time, which is the time of this difference, may be selected as the optimal one by taking time differences of multiple patterns and comparing them, but a range of about 3 to 10 minutes was a suitable range. Also, the data used in the calculation is the same as that shown in FIG. 7. As shown in FIG. 5, even in the time zone with a steady deviation in the same stage occurring in the second half of the time, the evaluation index does not continue to rise and does not continuously exceed the threshold value, so it is not continuously determined as an abnormality. Also, in the example shown in FIG. 7, it is possible to detect short-time temporal variations that were difficult to understand because the evaluation index continuously increased due to the influence of the steady deviation. Thus, it can be seen that this is a useful method for improving the accuracy of abnormality diagnosis when the steady deviation of the shaft pressure is not regarded as a major operation deterioration.

[0040] Next, the evaluation index difference integrated value calculation means 17 determines whether an abnormality has occurred in the blast furnace. The determination result is shown in FIG. 6. In the example shown in FIG. 6, the absolute value of the time difference value of the evaluation index was calculated with the first predetermined time being 5 minutes, and the integrated value of the absolute values was calculated with the second predetermined time being 10 minutes. Regarding the second predetermined time, it is advisable to determine it by examining actual data. However, in the case of the blast furnace operation data used this time, it is suitable to set it in the range of 5 minutes to 20 minutes, and a range of 10 minutes to 15 minutes was even better. Therefore, here it was determined that an integration time of 10 minutes was appropriate from the perspective of detection accuracy. Also, since it is affected by the aforementioned difference time, it is advisable to make the determination while considering the difference time as well. As shown in FIG. 6, in addition to obtaining the same effect as the example shown in FIG. 5, the noisy up and down variations of the evaluation index are suppressed compared to the example shown in FIG. 5. As a result, when an abnormality occurs, the evaluation index continuously exceeds the threshold value, and it is possible to continuously indicate that it is in an abnormal state during the abnormal state.

[0041] The embodiments to which the invention made by the present inventors is applied have been described above. However, the present invention is not limited by the description and drawings that form a part of the disclosure of the present invention according to this embodiment. That is, all other embodiments, examples, operation techniques, etc. made by those skilled in the art based on this embodiment are included in the scope of the present invention.

Industrial Applicability

[0042] According to the present invention, it is possible to provide a blast furnace abnormality determination device and an abnormality determination method capable of accurately determining blast furnace abnormalities. Further, according to the present invention, it is possible to provide a blast furnace operation method, an operation system, a blast furnace abnormality determination server device, a program for the blast furnace abnormality determination server device, and a display terminal device that can operate the blast furnace stably.

Explanation of Symbols

[0043] 1 Blast furnace abnormality determination device 11 Sensor signal acquisition means 12 Evaluation index calculation means 13 Evaluation index difference value calculation means 14 Determination means 15 Determination data transmission means 16 Evaluation index calculation model construction means 17 Evaluation index difference integrated value calculation means 21 Data collection device 22 Sensor

Claims

1. Sensor signal acquisition means for acquiring measurement data of a plurality of sensors installed at different positions in the blast furnace; Evaluation index calculation means for calculating a unified evaluation index indicating the furnace condition of the blast furnace from the measurement data acquired by the sensor signal acquisition means; Evaluation index difference value calculation means for calculating an evaluation index difference value which is the absolute value of the time difference that is the change amount of the evaluation index in a first predetermined time range calculated by the evaluation index calculation means; Judgment means for judging an abnormality of the blast furnace based on the evaluation index difference value calculated by the evaluation index difference value calculation means, and outputting the judged result and the data used for the judgment; Comprising; The sensor is a pressure sensor for detecting the shaft pressure of the blast furnace; The pressure sensors are arranged in a plurality of stages in the vertical direction of the furnace body in the shaft part of the blast furnace, and are arranged at equal intervals in the circumferential direction in each stage; The evaluation index is the Q statistic calculated by principal component analysis; The first predetermined time range is 3 to 10 minutes; The judgment means judges that there is an abnormality in the blast furnace when the evaluation index difference value is equal to or greater than a first predetermined threshold value; An abnormality judgment device for a blast furnace.

2. Comprising evaluation index difference integrated value calculation means for calculating an evaluation index difference integrated value which is the integrated value of the evaluation index difference value in a second predetermined time range calculated by the evaluation index difference value calculation means; The judgment means judges an abnormality of the blast furnace based on the evaluation index difference value calculated by the evaluation index difference value calculation means or the evaluation index difference integrated value calculated by the evaluation index difference integrated value calculation means, and outputs the judged result and the data used for the judgment; The second predetermined time range is 10 to 15 minutes which is equal to or greater than the first predetermined time range; The judgment means judges that there is an abnormality in the blast furnace when the evaluation index difference integrated value continuously is equal to or greater than a second predetermined threshold value. The abnormality judgment device for a blast furnace according to Claim 1.

3. The evaluation index calculation means calculates the evaluation index using a statistical learning model that outputs an evaluation index obtained by standardizing the furnace condition of the blast furnace based on the measurement data of the sensors in the normal state of the blast furnace. The abnormality judgment device for a blast furnace according to Claim 1 or 2.

4. A sensor signal acquisition step of acquiring measurement data of a plurality of sensors installed at different positions in the blast furnace; An evaluation index calculation step of calculating a unified evaluation index indicating the furnace condition of the blast furnace from the measurement data acquired in the sensor signal acquisition step; An evaluation index difference value calculation step of calculating an evaluation index difference value which is the absolute value of a time difference that is the amount of change in the evaluation index calculated in the evaluation index calculation step within a first predetermined time range; A determination step of determining an abnormality of the blast furnace based on the evaluation index difference value calculated in the evaluation index difference value calculation step, and outputting the determined result and the data used for the determination; comprising; The sensor is a pressure sensor that detects the shaft pressure of the blast furnace; The pressure sensors are arranged in a plurality of stages in the vertical direction of the furnace body in the shaft section of the blast furnace, and are arranged at equal intervals in the circumferential direction in each stage; The evaluation index is a Q statistic calculated by principal component analysis; The first predetermined time range is 3 to 10 minutes; The determination means determines that there is an abnormality in the blast furnace when the evaluation index difference value is equal to or greater than a first predetermined threshold value; An abnormality determination method for a blast furnace.

5. An evaluation index difference integrated value calculation step of calculating an evaluation index difference integrated value which is the integrated value of the evaluation index difference value within a second predetermined time range calculated in the evaluation index difference value calculation step; In the determination step, an abnormality of the blast furnace is determined based on the evaluation index difference value calculated in the evaluation index difference value calculation step or the evaluation index difference integrated value calculated in the evaluation index difference integrated value calculation step, and the determined result and the data used for the determination are output; The second predetermined time range is 10 to 15 minutes which is equal to or greater than the first predetermined time range; The determination means determines that there is an abnormality in the blast furnace when the evaluation index difference integrated value continuously is equal to or greater than a second predetermined threshold value. The abnormality determination method for a blast furnace according to claim 4.

6. The evaluation index calculation step includes a step of calculating the evaluation index using a statistical learning model that outputs an evaluation index obtained by standardizing the furnace condition state of the blast furnace based on the measurement data of the sensor in the normal state of the blast furnace. The abnormality determination method for a blast furnace according to claim 4 or 5.

7. An operation method for a blast furnace, which operates the blast furnace while determining whether the blast furnace is in an abnormal state using the abnormality determination method for a blast furnace according to claim 4 or 5.

8. An operation method for a blast furnace, which operates the blast furnace while determining whether the blast furnace is in an abnormal state using the abnormality determination method for a blast furnace according to claim 6.

9. An abnormality determination device for a blast furnace that determines an abnormality of the blast furnace; A display device connected to the abnormality determination device of the blast furnace via a network and displaying information output from the abnormality determination device of the blast furnace, comprising: The abnormality determination device of the blast furnace is sensor signal acquisition means for acquiring measurement data of a plurality of sensors installed at different positions of the blast furnace; evaluation index calculation means for calculating a unified evaluation index indicating the furnace condition of the blast furnace from the measurement data acquired by the sensor signal acquisition means; evaluation index difference value calculation means for calculating an evaluation index difference value which is the absolute value of the time difference that is the change amount of the evaluation index in the first predetermined time range calculated by the evaluation index calculation means; determination means for determining an abnormality of the blast furnace based on the evaluation index difference value calculated by the evaluation index difference value calculation means, and outputting the determined result and the data used for the determination; comprising: The sensor is a pressure sensor for detecting the shaft pressure of the blast furnace, The pressure sensors are arranged in a plurality of stages in the vertical direction of the furnace body in the shaft section of the blast furnace, and are arranged at equal intervals in the circumferential direction in each stage. The evaluation index is the Q statistic calculated by principal component analysis. The first predetermined time range is 3 to 10 minutes. The determination means determines that there is an abnormality in the blast furnace when the evaluation index difference value is equal to or greater than a first predetermined threshold value. An operating system for a blast furnace.

10. An abnormality determination server device for a blast furnace that constructs an operating system for a blast furnace together with a data collection device that acquires and stores measurement data from sensors installed in the blast furnace and a display terminal device that acquires and displays abnormality determination information from the abnormality determination server device of the blast furnace, sensor signal acquisition means for acquiring measurement data of a plurality of sensors installed at different positions of the blast furnace from the data collection device; evaluation index calculation means for calculating a unified evaluation index indicating the furnace condition of the blast furnace from the measurement data acquired by the sensor signal acquisition means; evaluation index difference value calculation means for calculating an evaluation index difference value which is the absolute value of the time difference that is the change amount of the evaluation index in the first predetermined time range calculated by the evaluation index calculation means; determination means for determining an abnormality of the blast furnace based on the evaluation index difference value calculated by the evaluation index difference value calculation means, and outputting the determined result and the data used for the determination; determination data transmission means for transmitting abnormality determination information including the determined result and the data used for the determination; comprising: The sensor is a pressure sensor for detecting the shaft pressure of the blast furnace, The pressure sensor is arranged in a plurality of stages in the vertical direction of the furnace body in the blast furnace shaft section, and is arranged at equal intervals in the circumferential direction in each stage. The evaluation index is the Q statistic calculated by principal component analysis. The first predetermined time range is 3 to 10 minutes. The determination means determines that there is an abnormality in the blast furnace when the evaluation index difference value is equal to or greater than a first predetermined threshold value. An abnormal determination server device for a blast furnace.

11. A program for an abnormal determination server device of a blast furnace that constructs an operation system of a blast furnace together with a data collection device that acquires and stores measurement data from sensors installed in the blast furnace and a display terminal device that acquires and displays abnormal determination information from the abnormal determination server device of the blast furnace, causing a computer to sensor signal acquisition means for acquiring measurement data of a plurality of sensors installed at different positions in the blast furnace from the data collection device; evaluation index calculation means for calculating a unified evaluation index indicating the furnace condition of the blast furnace from the measurement data acquired by the sensor signal acquisition means; evaluation index difference value calculation means for calculating an evaluation index difference value that is the absolute value of the time difference, which is the amount of change in the first predetermined time range of the evaluation index calculated by the evaluation index calculation means; determination means for determining an abnormality in the blast furnace based on the evaluation index difference value calculated by the evaluation index difference value calculation means, and outputting the determined result and the data used for the determination; determination data transmission means for transmitting abnormal determination information including the determined result and the data used for the determination; function as The sensor is a pressure sensor that detects the shaft pressure of the blast furnace. The pressure sensor is arranged in a plurality of stages in the vertical direction of the furnace body in the blast furnace shaft section, and is arranged at equal intervals in the circumferential direction in each stage. The evaluation index is the Q statistic calculated by principal component analysis. The first predetermined time range is 3 to 10 minutes. The determination means determines that there is an abnormality in the blast furnace when the evaluation index difference value is equal to or greater than a first predetermined threshold value. A program for an abnormal determination server device of a blast furnace.

12. A data collection device that acquires and stores measurement data from sensors installed in a blast furnace, a sensor signal acquisition means that acquires measurement data of a plurality of sensors installed at different positions in the blast furnace from the data collection device, an evaluation index calculation means that calculates a unified evaluation index indicating the furnace condition of the blast furnace from the measurement data acquired by the sensor signal acquisition means, an evaluation index difference value calculation means that calculates an evaluation index difference value that is the absolute value of the time difference that is the amount of change in the first predetermined time range of the evaluation index calculated by the evaluation index calculation means, a determination means that determines an abnormality in the blast furnace based on the evaluation index difference value calculated by the evaluation index difference value calculation means and outputs the determination result and the data used for the determination, and a determination data transmission means that transmits abnormality determination information including the determination result and the data used for the determination, wherein the sensor is a pressure sensor that detects the shaft pressure of the blast furnace, the pressure sensors are arranged in a plurality of stages in the vertical direction of the furnace body in the shaft section of the blast furnace, and are arranged at equal intervals in the circumferential direction in each stage, the evaluation index is a Q statistic calculated by principal component analysis, the first predetermined time range is 3 to 10 minutes, and the determination means determines that there is an abnormality in the blast furnace when the evaluation index difference value is equal to or greater than a first predetermined threshold value, a display terminal device that constructs an operation system of the blast furnace together with the abnormality determination server device of the blast furnace, A display terminal device that acquires and displays the abnormality determination information from the abnormality determination server device of the blast furnace via a network.

13. Comprising an evaluation index difference integrated value calculation means that calculates an evaluation index difference integrated value that is the integrated value of the evaluation index difference value in the second predetermined time range calculated by the evaluation index difference value calculation means, The determination means determines an abnormality in the blast furnace based on the evaluation index difference value calculated by the evaluation index difference value calculation means or the evaluation index difference integrated value calculated by the evaluation index difference integrated value calculation means, and outputs the determination result and the data used for the determination, The second predetermined time range is 10 to 15 minutes that is equal to or greater than the first predetermined time range, The determination means determines that there is an abnormality in the blast furnace when the evaluation index difference integrated value continuously exceeds the second predetermined threshold value. The operation system of the blast furnace according to claim 9.

14. An evaluation index difference integrated value calculation means for calculating an integrated value of the evaluation index difference value in a second predetermined time range, which is calculated by the evaluation index difference value calculation means, is provided. The determination means determines an abnormality of the blast furnace based on the evaluation index difference value calculated by the evaluation index difference value calculation means or the evaluation index difference integrated value calculated by the evaluation index difference integrated value calculation means, and outputs the determined result and the data used for the determination. The second predetermined time range is 10 to 15 minutes that is equal to or longer than the first predetermined time range. The determination means determines that there is an abnormality in the blast furnace when the evaluation index difference integrated value continues to be equal to or greater than the second predetermined threshold value. The blast furnace abnormality determination server device according to claim 10.

15. A computer is caused to function as an evaluation index difference integrated value calculation means for calculating an integrated value of the evaluation index difference value in a second predetermined time range, which is calculated by the evaluation index difference value calculation means. The determination means determines an abnormality of the blast furnace based on the evaluation index difference value calculated by the evaluation index difference value calculation means or the evaluation index difference integrated value calculated by the evaluation index difference integrated value calculation means, and outputs the determined result and the data used for the determination. The second predetermined time range is 10 to 15 minutes that is equal to or longer than the first predetermined time range. The determination means determines that there is an abnormality in the blast furnace when the evaluation index difference integrated value continues to be equal to or greater than the second predetermined threshold value. A program for the blast furnace abnormality determination server device according to claim 11.

16. A display terminal device for constructing a blast furnace operation system together with the blast furnace abnormality determination server device according to claim 12, which acquires and displays the abnormality determination information from the blast furnace abnormality determination server device via a network.

Images