JP7031512B2 - Monitoring work support system for steel plants - Google Patents

Description

The present invention relates to a monitoring work support system for a steel plant.

Due to advances in science and technology so far, many processes in steel plants have advanced equipment automation by making full use of control technology and system technology. However, it has not reached the point of full automation of the entire factory, and today, humans are responsible for tasks that require flexible judgment, which is difficult for machines, and the operation of the entire factory is carried out smoothly.

Workers monitor the automated equipment from an operation room (called a palpit) located in a location where the equipment can be seen. In the operation room, in order to grasp the operating status of the equipment, a monitor that shows the equipment and the material to be rolled taken by multiple cameras, a monitor that outputs the operating status of the equipment and an alarm, and the rolled measured by the sensor. A monitor that outputs a graph of physical quantities such as materials and actuators will be installed. The worker makes a judgment of the correction operation by confirming them. In addition, buttons, levers, and input terminals for modifying the operation of the equipment are installed on the operation panel facing the operator. Workers make corrections to the operation of the equipment as necessary, adjust the production order and timing so that steel production of the entire factory can be performed efficiently, and the indicated value of the product depending on the operating status of the equipment. Many operations are performed, such as changing the to the extent possible.

In particular, when the operator monitors a monitor that outputs a graph of physical quantities such as the material to be rolled and the actuator measured by the sensor, the waveform must be visually confirmed to determine the occurrence of an abnormality. In addition, when a steel material with conditions that require caution (for example, a specific steel grade) is rolled, first, grasp the target condition from the information on the monitor, and visually check the material to be rolled if necessary. It is necessary to confirm with, confirm the operation data on the screen, and judge the operation method in consideration of the combination of the conditions of the confirmed contents. Since these are human judgments, they may be overlooked and the operation may be mistaken.

By supporting this series of monitoring work in the operation room, the work efficiency is improved, the monitoring work is facilitated, and the oversight of abnormalities is reduced, thereby improving the quality of the product and burdening the operator. A support system that can be mitigated is desired.

For example, Patent Document 1 discloses a system that learns learning data consisting of normal cases based on the degree of similarity and the presence or absence of abnormalities and detects abnormalities in observation data using the learning data in order to reduce the burden on the operator. ing.

The applicant recognizes the documents described below, including the above-mentioned documents, as related to the present invention.

Japanese Unexamined Patent Publication No. 2010-191556 International Publication No. 2015/177870 Japanese Unexamined Patent Publication No. 6-313721

In Patent Document 1, the accuracy of abnormality detection is certainly improved if sufficient learning data is prepared. However, it is difficult to prepare sufficient learning data for each of various product specifications, and it is not always practical. Practically, by making the best use of the sample data that can be prepared, even if the product specifications do not always match, visually check the graph waveform of the physical quantity of the material to be rolled, the actuator, etc. to detect the occurrence of an abnormality. It is desirable to be able to support the monitoring work of the workers who make decisions.

The present invention has been made to solve the above-mentioned problems, and is a steel plant capable of supporting the monitoring work of workers who visually confirm the data waveform over the entire length of the material to be rolled and judge the occurrence of an abnormality. The purpose is to provide a monitoring work support system for use.

The monitoring work support system for a steel plant according to the present invention provides information and other data obtained by visually observing the state of rolling of the material to be rolled and the display of the information monitor in the monitoring work in the operation room of the steel plant. It supports a series of work to determine the necessary operation by combining the conditions according to the above, or to remove the abnormality by immediately grasping the occurrence of an abnormality in the equipment and executing the operation.

In order to achieve the above object, the monitoring work support system for a steel plant according to the present invention includes a data storage unit, an abnormality chart pattern registration unit, a similarity determination unit, and a message output unit.

The data storage unit stores the actual data of the total length data consisting of the measured values of the predetermined data items at each point in the longitudinal direction of the material to be rolled. The data items of the total length data are, for example, the plate thickness on the output side of the finish rolling mill, the plate width on the output side of the finish rolling mill, the plate thickness on the output side of the rough rolling mill, the plate width on the output side of the rough rolling mill, and the plate width on the output side of the finish rolling mill. The temperature on the side, the temperature on the exit side of the heating furnace, etc. The full-length data is a set of time from the start of passage of one cutting edge of the material to be rolled through the position near the equipment determined by each data item to the completion of passage of the tail end of the material to be rolled. It means the data collected at the pitch.

The abnormality chart pattern registration unit registers at least one abnormal full-length data for a data item. As the abnormal total length data, the actual data when an abnormality has occurred in the equipment in the past and the created data showing a typical abnormality pattern are registered.

The similarity determination unit determines that the waveforms are similar when the square root of the mean square of the deviations between D1_dev [i] and D2_dev [i] is smaller than the threshold value. Here, D1_dev [i] is the deviation between the value D1 [i] at each point [i] (i = 1, ..., N) of the actual data and the average value ave1 of the actual data. D2_dev [i] is the deviation between the value D2 [i] at each point [i] of the abnormal full-length data and the mean value ave2 of the abnormal full-length data.

In this way, by judging the similarity based on the square root of the mean square of the deviations between D1_dev [i] and D2_dev [i], the values of D1 [i] and D2 [i] at each point [i] are large. Regardless of whether or not there is a difference, it can be determined whether or not the "waveforms" of these full-length data are similar. For example, it is determined whether or not the waveform of the abnormal total length data prepared for a certain product specification (for example, the target plate thickness of 1 mm) is similar to the waveform of the actual data of a different product specification (for example, the target plate thickness of 3 mm). be able to. That is, if the data items (for example, the plate thickness on the output side of the finishing rolling mill) are common, it is possible to determine the similarity of the waveforms even if the target plate thickness is different. Therefore, even if the amount of abnormal total length data that can be prepared in advance for each product specification is small, it is possible to determine whether or not the waveforms of various actual data are abnormal.

The message output unit outputs a pre-registered warning message when the similarity determination unit determines that the waveforms are similar. Preferably, the message output unit determines that the waveform of the actual data stored in the data storage unit by the similarity determination unit is similar to the waveform of the specified abnormal full-length data, and the product specifications of the material to be rolled. When it is determined that the one-point data related to the specified condition is satisfied, a pre-registered warning message is output.

According to the monitoring work support system for a steel plant according to the present invention, it is possible to support the monitoring work of a worker who visually confirms the data waveform over the entire length of the material to be rolled and determines the occurrence of an abnormality. In addition, by supporting the monitoring work of the workers, it is possible to sufficiently support a series of work for detecting the occurrence of an abnormality in the plant equipment at an early stage and removing the abnormality. As a result, the efficiency of the work is improved and the work becomes easier, so that it is possible to reduce the oversight of abnormalities, improve the quality of the product, and reduce the burden on the operator.

It is a schematic diagram which shows the steel plant to which the monitoring work support system which concerns on Embodiment 1 of this invention is applied, and the flow of data used in the system. It is a schematic diagram which shows the outline of the pattern determination of the total length data performed in the calculation part of the monitoring work support system which concerns on Embodiment 1 of this invention. It is a graph for demonstrating the similarity determination of the total length data in the calculation part of a monitoring work support system. It is a figure for demonstrating the condition determination for message output in the calculation part of a monitoring work support system. It is a conceptual diagram which shows the hardware configuration example of the processing circuit which a monitoring work support system has.

Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. The elements common to each figure are designated by the same reference numerals, and duplicate description will be omitted.

Embodiment 1.
(System configuration)
FIG. 1 is a schematic diagram showing a steel plant to which a monitoring work support system is applied and a data flow used in the system.

In the rolling line 2, the high-temperature slab (material to be rolled 1) heated in the heating furnace 2a is conveyed by a transfer roll and thinly rolled to the target plate thickness by the rough rolling mill 2b and the finishing rolling mill 2c, and at the same time, the target. It is processed to the width of a plate, cooled, and finally rolled up by a coiler 2d to manufacture a product (coil).

The control system 3 transmits command data d1 for operation to each facility of the rolling line 2. Further, sensors are attached to each equipment of the rolling line 2, and the control system 3 collects the actual data measured by them. The actual data is roughly classified into two types: actual data d2 used in the control system 3 and actual data d4 used for analysis and evaluation without being used in the control system 3.

The monitoring work support system 4 includes a data storage unit 5, a calculation unit 6, and an information display unit 7.

The data storage unit 5 collects and stores the actual data d2 used in the control system 3, the data d3 which is a combination of the intermediate calculation data and the calculation result data in the control system, and the above-mentioned actual data d4. The collected data includes full-length data and one-point data for each data item. The data items include a full-length data item and a one-point data item. The types of total length data items include the plate thickness on the output side of the finish rolling mill, the plate width on the output side of the finish rolling mill, the plate thickness on the output side of the rough rolling mill, the plate width on the output side of the rough rolling mill, and the plate width on the output side of the finish rolling mill. There are temperature, temperature on the outside of the heating furnace, etc. The total length data consists of measured values of predetermined data items at each point in the longitudinal direction of the material to be rolled. More specifically, the full-length data is from the time when the cutting edge of one material to be rolled starts to pass through the position near the equipment determined by each data item until the end of the material to be rolled is completed. Means the data collected at a fixed time pitch as a group. The one-point data refers to the product specifications of the material to be rolled, and the types of one-point data items include, for example, a steel type, a target plate thickness, and a target plate width.

The calculation unit 6 detects an abnormality in the data d5 stored in the data storage unit 5, and outputs a warning message for supporting the monitoring work of the worker. The details of the calculation unit 6 will be described later. The information display unit 7 includes a monitor that displays a warning message output by the calculation unit 6.

The worker 100 displayed a monitor 8 showing the equipment and the material to be rolled taken by a plurality of cameras, and a graph outputting the operating status of the equipment, an alarm, and the physical quantity of the material to be rolled and the actuator measured by the sensor. The information from the monitor 9 and the glass window 10 in which the material to be rolled can be seen being rolled by the equipment is visually observed. At the same time, with the support of the warning message displayed on the information display unit 7, the worker 100 can perform a series of monitoring work and a series of work for removing the abnormality.

(Calculation department of monitoring work support system)
Specific processing in the calculation unit 6 of the monitoring work support system 4 will be described with reference to FIGS. 2 to 4. The calculation unit 6 includes an abnormality chart pattern registration unit 61, a similarity determination unit 62, a message condition registration unit 63, and a message output unit 64.

FIG. 2 is a schematic diagram showing an outline of pattern determination of full-length data performed by the calculation unit 6 of the monitoring work support system 4.

In the abnormality chart pattern registration unit 61, abnormality chart patterns indicating abnormal total length data are previously grouped and registered for each total length data item. The anomaly chart pattern is defined by a standard that prompts the operator to check if a waveform similar to this is found in the actual data stored in the data storage unit 5. Since the length of the product (coil) differs depending on the specifications, the abnormality chart pattern is normalized so that it can be compared with various actual data.

The similarity determination unit 62 determines whether or not the waveform of the actual data related to the total length data stored in the data storage unit 5 is similar to the waveform of the abnormality chart pattern registered in the abnormality chart pattern registration unit 61.

FIG. 3 is a diagram for explaining the similarity determination between the actual data of the full length data and the abnormality chart pattern. Here, as an example, the data item is the plate thickness on the exit side of the finish rolling mill.

FIG. 3A is one of the actual data stored in the data storage unit 5, and is related to the total length data regarding the plate thickness on the output side of the finish rolling mill. The actual data is normalized so that it can be compared with the abnormal chart pattern. D1 [i] (i = 1, ..., N) means the plate thickness on the exit side of the finish rolling mill at each point [i] from the tip to the tail of the material to be rolled. ave1 is the average value of D1 [i]. The similarity determination unit 62 calculates the deviation D1_dev [i] between D1 [i] and ave1 at each point [i].
D1_dev [i] = D1 [i] --ave1… (1)

FIG. 3B is an abnormal chart pattern regarding the plate thickness on the exit side of the finish rolling mill registered in the abnormal chart pattern registration unit 61. D2 [i] (i = 1, ..., N) means the plate thickness on the exit side of the finish rolling mill at each point [i] from the tip to the tail of the material to be rolled. ave2 is the average value of D2 [i]. The similarity determination unit 62 calculates the deviation D2_dev [i] between D2 [i] and ave2 at each point [i].
D2_dev [i] = D2 [i] --ave2… (2)

Then, the similarity determination unit 62 calculates the distance between D1_dev [i] and D2_dev [i] for each point [i]. Specifically, the square root of the mean square of the deviation between D1_dev [i] and D2_dev [i] (mean square error square root) is calculated. When this value is smaller than the threshold value, it is determined that the actual data and the waveform of the abnormal chart pattern are similar.

In this way, by judging the similarity based on the square root of the mean square of the deviations between D1_dev [i] and D2_dev [i], the values of D1 [i] and D2 [i] at each point [i] are large. Regardless of whether or not there is a difference, it can be determined whether or not the "waveforms" of these full-length data are similar. For example, it is determined whether or not the waveform of the abnormal total length data prepared for a certain product specification (for example, the target plate thickness of 1 mm) is similar to the waveform of the actual data of a different product specification (for example, the target plate thickness of 3 mm). be able to. That is, if the data items (for example, the plate thickness on the output side of the finishing rolling mill) are common, it is possible to determine the similarity of the waveforms even if the target plate thickness is different. Therefore, even if the amount of abnormal total length data that can be prepared in advance for each product specification is small, it is possible to determine whether or not the waveforms of various actual data are abnormal.

In the message condition registration unit 63, the determination condition when each warning message is output and the content of the message are registered as a character string. The determination condition may be only the full length data or may be a combination of the full length data and the one-point data.

In the case of only the full-length data, the error chart pattern and the warning message to be notified to the operator are registered in the message condition registration unit 63 in association with each other for the predetermined data item. The message output unit 64 outputs a related warning message to the information display unit 7 when the actual data similar to the abnormality chart pattern registered in the message condition registration unit 63 is found. The worker 100 can receive support by the warning message displayed on the information display unit 7.

In the case of a combination of the full-length data and the one-point data, the message condition registration unit 63 notifies the operator of the judgment conditions effective for determining the monitoring work in which the full-length data and the one-point data are combined, as shown in FIG. It is registered in association with the warning message that should be. The data items that can be used as the determination condition for the one-point data are the items stored in the data storage unit 5, and can be determined by an inequality sign or a simple character string determination.

The message output unit 64 determines that the waveform of the actual data stored in the data storage unit 5 by the similarity determination unit 62 is similar to the waveform of the designated abnormal chart pattern, and the predetermined one-point data is designated. When it is determined that the condition is satisfied, the warning message associated with the determination condition is output to the information display unit 7. In the example of FIG. 4, the full-length data for the data item 1 registered in the data storage unit 5 is similar to the abnormality pattern A, the data item 2 is similar to the pattern B, and the one-point data a matches the condition X. When all of the above are satisfied, the warning message associated with this judgment condition is output. The worker 100 can receive support by the warning message displayed on the information display unit 7.

There are multiple timings for condition judgment for message output, and condition judgment can be executed at the timing when actual data is saved in each process, and a warning message can be output. For example, it is executed at the timing when the material 1 to be rolled is rolled by the upstream rough rolling mill 2b, and a warning message leading to improvement of rolling of the downstream finish rolling mill 2c is output to support the monitoring work of the operator. be able to.

As described above, according to the monitoring work support system according to the present embodiment, it is possible to support the monitoring work of the worker who visually confirms the data waveform over the entire length of the material to be rolled and determines the occurrence of an abnormality. In addition, by supporting the monitoring work of the workers, it is possible to sufficiently support a series of work for detecting the occurrence of an abnormality in the plant equipment at an early stage and removing the abnormality. As a result, the efficiency of the work is improved and the work becomes easier, so that abnormalities are less likely to be overlooked, the quality of the product can be improved, and the burden on the operator can be reduced.

Further, as the full-length data item, if the item corresponds to the chart displayed on the monitor 9 or is not displayed (for example, the temperature on the exit side of the heating furnace) but is stored in the data storage unit 5, an abnormal chart pattern is displayed. It can be registered and used to assist in making decisions. Therefore, it is possible to detect an abnormality even in data that is not normally displayed on the monitor and cannot be seen by the operator.

(Hardware configuration example)
FIG. 5 is a conceptual diagram showing a hardware configuration example of a processing circuit included in the above-mentioned monitoring work support system. Each of the above-mentioned functions is realized by a processing circuit. In one aspect, the processing circuit comprises at least one processor 91 and at least one memory 92. In another aspect, the processing circuit comprises at least one dedicated hardware 93.

When the processing circuit includes a processor 91 and a memory 92, each function is realized by software, firmware, or a combination of software and firmware. At least one of the software and firmware is written as a program. At least one of the software and firmware is stored in memory 92. The processor 91 realizes each function by reading and executing the program stored in the memory 92.

When the processing circuit includes dedicated hardware 93, the processing circuit may be, for example, a single circuit, a composite circuit, a programmed processor, or a combination thereof. Each function is realized by a processing circuit.

Although the embodiments of the present invention have been described above, the present invention is not limited to the above-described embodiments, and can be variously modified and implemented without departing from the spirit of the present invention.

1 Material to be rolled 2 Rolling line 2a Heating furnace 2b Rough rolling machine 2c Finishing rolling machine 2d Koyler 3 Control system 4 Monitoring work support system 5 Data storage unit 6 Calculation unit 7 Information display unit 8, 9 Monitor 10 Glass window 61 Abnormal chart pattern Registration unit 62 Similarity judgment unit 63 Message condition registration unit 64 Message output unit 91 Processor 92 Memory 93 Hardware 100 Worker

Claims (1)

A data storage unit that stores actual data about the total length data consisting of measured values of predetermined data items at each point in the longitudinal direction of the material to be rolled, and a data storage unit.
An abnormality chart pattern registration unit that registers at least one abnormal full-length data for the data item,
Let D1_dev [i] be the deviation between the value D1 [i] at each point [i] (i = 1, ..., N) of the actual data and the average value ave1 of the actual data.
When the deviation between the value D2 [i] at each point [i] of the abnormal full-length data and the average value ave2 of the abnormal full-length data is D2_dev [i],
When the square root of the mean square of the deviation between D1_dev [i] and D2_dev [i] is smaller than the threshold value, the similarity judgment unit that determines that the waveforms are similar, and
A message output unit that outputs a pre-registered warning message when it is determined by the similarity determination unit that the waveforms are similar is provided .
The message output unit determines that the waveform of the actual data stored in the data storage unit by the similarity determination unit is similar to the waveform of the specified abnormal full-length data, and the rolled material is Output a pre-registered warning message when it is determined that the one-point data related to the product specifications meets the specified conditions.
A monitoring work support system for steel plants featuring.

Images