Roll management device

Abstract

Provided is a roll management device capable of determining the state of a rolling mill roll based on information on the past state of the rolling mill roll and prompting the application method of the rolling mill roll. The roll management device has: a data acquisition section that acquires physical quantities related to a plurality of rolling mill rolls at the time of rolling and application conditions of rolling; a data storage section that accumulates the physical quantities and the application conditions of rolling acquired by the data acquisition section up to the previous rolling; a state determination section that, for the application conditions of rolling accumulated in the data storage section that are the same as or similar to the application conditions of rolling of a specific rolling mill roll used for rolling, reads the related physical quantities, and determines the state of the specific rolling mill roll based on the related physical quantities; and a recommended application method determination section that, based on the state of the specific rolling mill roll determined by the state determination section, prompts the recommended application method for the specific rolling mill roll.

Description

Technical Field

[0001] The present application relates to a roll management device. Background Art

[0002] Patent Document 1 discloses a roll management device that can eliminate eccentricity of rolling rolls.

[0003] Prior art literature

[0004] Patent Literature

[0005] Patent Document 1: Japanese Patent No. 5821527 Summary of the Invention

[0006] Problems to be solved by the invention

[0007] However, the roll management device described in Patent Document 1 cannot detect the main cause of eccentricity of the rolling rolls, and therefore cannot appropriately use the rolling rolls in the next rolling operation.

[0008] The present application is made to solve the above-mentioned problem. An object of the present application is to provide a roll management device that can appropriately utilize rolling rolls.

[0009] Means for solving problems

[0010] The roller management device related to the present application comprises: a data acquisition unit, which collects physical quantities related to multiple rolling rollers during rolling and rolling application condition data; a data storage unit, which accumulates the physical quantities and rolling application condition data collected by the data acquisition unit up to the previous rolling; a state determination unit, which reads the relevant physical quantities for the rolling application condition data accumulated in the data storage unit that are the same as or similar to the rolling application condition data of the specific rolling roller used for rolling, and determines the state of the specific rolling roller based on the relevant physical quantities; and a recommended application method determination unit, which prompts a recommended application method for the specific rolling roller based on the state of the specific rolling roller determined by the state determination unit.

[0011] Effects of the Invention

[0012] According to the present application, the roll management device presents a recommended application method for a specific rolling roll according to the state of the specific rolling roll, thereby enabling appropriate application of the rolling roll. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 This is a configuration diagram of a roll management system applied to the roll management device of the first embodiment.

[0014] Figure 2 This is a configuration diagram of the roll management device according to the first embodiment.

[0015] Figure 3 This is a graph showing an example of the roll physical quantity signal, the material entry detection signal, the material departure detection signal, and the material total length measurement signal of the roll management device according to the first embodiment.

[0016] Figure 4 This is a graph showing examples of pre-processing roll phenomenon data and post-processing roll phenomenon data in the roll management device according to the first embodiment.

[0017] Figure 5 This is a diagram showing an example of a delamination phenomenon history database of the roll management device according to the first embodiment.

[0018] Figure 6 This is a diagram showing an example of the state determination threshold database of the roll management device according to the first embodiment.

[0019] Figure 7 This is a diagram showing an example of a status pattern database of the roll management device according to the first embodiment.

[0020] Figure 8 This is a diagram showing an example of the recommended application method database of the roll management device according to the first embodiment.

[0021] Figure 9 This is a flowchart for explaining an outline of the operation of the roll management device according to the first embodiment.

[0022] Figure 10 This is a hardware configuration diagram of the roll management device according to the first embodiment.

[0023] Figure 11 This is a configuration diagram of a roll management device according to the second embodiment.

[0024] Figure 12 This is a configuration diagram of a roll management device according to a third embodiment.

[0025] Figure 13 This is a configuration diagram of a roll management device according to a fourth embodiment.

[0026] Figure 14 This is a configuration diagram of a roll management device according to a fifth embodiment.

[0027] Figure 15 This is a configuration diagram of a roll management device according to a sixth embodiment.

[0028] Figure 16 This is a configuration diagram of a roll management device according to a seventh embodiment.

[0029] Label Description

[0030] 1…Roller management device; 2…Data acquisition unit; 2a…Data extraction unit; 2b…Data pre-processing unit; 3…Data quantification unit; 3a…Basic statistics calculation unit; 3b…Frequency analysis unit; 3c…Data model estimation unit; 3d…Quantitative data manual input unit; 4…Data storage unit; 4a…Data storage unit; 4b…Stratified phenomenon history data reading unit; 4c…Stratified phenomenon history database; 5…State determination unit; 5a…State phenomenon database; 5b…State determination unit; 5c…State determination threshold calculation unit; 5d…State determination unit Fixed logic inference unit; 5e…state occurrence prediction unit; 6…recommended application method determination unit; 6a…recommended application method database; 6b…recommended application method determination unit; 7…user; 11…rolling machine; 12…process computer; 21…upper rolling roller; 22…lower rolling roller; 31…roller physical quantity sensor; 32…material entry detection sensor; 33…material separation detection sensor; 34…material total length measurement sensor; 41…material before rolling; 42…material after rolling; 100a…processor; 100b…memory; 200…hardware. DETAILED DESCRIPTION

[0031] The embodiments will be described with reference to the accompanying drawings. In the drawings, the same or corresponding parts are given the same reference numerals, and the repeated description of the parts will be simplified or omitted as appropriate.

[0032] Implementation Method 1

[0033] Figure 1 This is a configuration diagram of a roll management system to which the roll management device according to the first embodiment is applied.

[0034] like Figure 1 As shown, the roll management system comprises a rolling mill 11 , a roll management device 1 and a process computer 12 .

[0035] The rolling mill 11 includes upper rolling rolls 21, lower rolling rolls 22, a roll physical quantity sensor 31, a material entry detection sensor 32, a material exit detection sensor 33, and a material total length measurement sensor 34. For example, the rolling mill 11 rolls ferrous and non-ferrous materials.

[0036] The upper rolling roll 21 and the lower rolling roll 22 sandwich the material and roll it. L is the total length of the rolled material 42. L1 is the center of the rolled material 42. L2 is the center of the rolled material 42.

[0037] The roller physical quantity sensor 31 is configured to be able to measure physical quantities related to the upper rolling roller 21. For example, the physical quantity related to the upper rolling roller 21 refers to the pressure applied to the upper rolling roller 21. For example, the physical quantity related to the upper rolling roller 21 refers to the displacement of the position of the upper rolling roller 21. For example, the physical quantity related to the upper rolling roller 21 refers to the vibration value of the rolling load of the upper rolling roller 21. For example, the physical quantity related to the upper rolling roller 21 refers to the rolling tension of the upper rolling roller 21. The roller physical quantity sensor 31 sends a roller physical quantity signal based on the physical quantity related to the upper rolling roller 21.

[0038] The material entry detection sensor 32 is configured to be able to detect the entry of the pre-rolled material 41. For example, the material entry detection sensor 32 detects the passage of the pre-rolled material 41 through its own detection range. For example, the material entry detection sensor 32 sends a material entry detection signal when detecting the entry of the pre-rolled material 41. For example, the material entry detection sensor 32 sends a material entry detection signal for the passage of the pre-rolled material 41 in its own detection range. For example, the material entry detection sensor 32 sends a material entry detection signal as a signal indicating whether the pre-rolled material 41 is detected at its own proximity position. For example, the material entry detection signal is a true value. For example, when the material entry detection sensor 32 detects the pre-rolled material 41 at its own proximity position, the material entry detection signal shows "1". For example, when the material entry detection sensor 32 does not detect the pre-rolled material 41 at its own proximity position, the material entry detection signal shows "0".

[0039] The material detachment detection sensor 33 is configured to be able to detect the detachment of the rolled material 42. For example, the material detachment detection sensor 33 detects the situation where the rolled material 42 passes through its own detection range. For example, the material detachment detection sensor 33 sends a material detachment detection signal when detecting the detachment of the rolled material 42. For example, the material detachment detection sensor 33 sends a material detachment detection signal for the passage of the rolled material 42 in its own detection range. For example, the material detachment detection signal is a true value. For example, when the material detachment detection sensor 33 detects the rolled material 42 at its own proximity position, the material detachment detection signal shows "1". For example, when the material detachment detection sensor 33 does not detect the rolled material 42 at its own proximity position, the material entry detection signal shows "0".

[0040] For example, the total material length measuring sensor 34 detects when the front end of the rolled material 42 passes through its own detection range. For example, the total material length measuring sensor 34 detects the time it takes for the front end of the rolled material 42 to pass through its own detection range. For example, the total material length measuring sensor 34 detects when the end of the rolled material 42 passes through its own detection range. For example, the total material length measuring sensor 34 detects the time it takes for the end of the rolled material 42 to pass through its own detection range. The total material length measuring sensor 34 sends a total material length measurement signal. For example, the total material length measurement signal is the length from the front end of the rolled material 42 to its own detection point at the measurement moment after the start of rolling. For example, assuming that the start time of rolling is time 0 and the end time of rolling is T, the total material length measurement signal at the end time T of rolling represents the total length L of the rolled material 42.

[0041] The roll management device 1 is arranged to be able to communicate with the rolling mill 11. The roll management device 1 is arranged to be able to communicate with the process computer 12.

[0042] For example, the process computer 12 is a general-purpose computer. The process computer 12 is configured to receive rolling application condition data from a production management computer (not shown). For example, the application condition data may be production instructions. For example, the application condition data may be manufacturing specifications. For example, the application condition data may include information such as the steel grade, size, and temperature of the rolled material. The process computer 12 calculates the rolling conditions based on the received information and transmits the calculated values.

[0043] Next, use Figure 2 The configuration of the roll management device 1 will be described.

[0044] Figure 2 This is a configuration diagram of the roll management device according to the first embodiment.

[0045] like Figure 2 As shown, the roll management device 1 includes a data collecting unit 2 , a data quantifying unit 3 , a data storing unit 4 , a state determining unit 5 , and a recommended application method determining unit 6 .

[0046] The data acquisition unit 2 receives roll physical quantity signals, material entry detection signals, material separation detection signals, and total material length measurement signals from the rolling mill 11. For example, the data acquisition unit 2 simultaneously receives the roll physical quantity signals, material entry detection signals, material separation detection signals, and total material length measurement signals. The data acquisition unit 2 includes a data extraction unit 2a and a data pre-processing unit 2b.

[0047] The data extraction unit 2a collects pre-processing roll phenomenon data based on signals received from the rolling mill 11. Pre-processing roll phenomenon data is information related to the upper rolling roll 21. For example, pre-processing roll phenomenon data is information obtained by extracting data within the range required for quantification from information related to the upper rolling roll 21. For example, pre-processing roll phenomenon data refers to rolling load vibration values. For example, pre-processing roll phenomenon data refers to rolling tension values. For example, pre-processing roll phenomenon data refers to rolling roll displacement values. For example, pre-processing roll phenomenon data includes a predetermined sampling period and a predetermined sampling time range. For example, pre-processing roll phenomenon data includes an appropriate sampling period and an appropriate sampling time range for quantifying phenomena related to the rolling rolls. As a specific example of a sampling period, when collecting data on roll eccentricity vibration, if the roll eccentricity frequency is approximately 2 Hz, the sampling frequency is quadrupled to account for sampling theorem and noise effects. In this case, a suitable sampling period is set to approximately 100 ms. For example, a suitable sampling time range includes timings such as after the start of rolling, midway through rolling, and at the end of rolling. For example, an appropriate sampling time range is set based on the position of the measurement point within the total length of the material. For example, the measurement point within the total length of the material may be the front end, the middle, or the rear end of the total length of the material. The data extraction unit 2a transmits the pre-processing roller phenomenon data.

[0048] The data pre-processing unit 2b receives the pre-processed roll phenomenon data from the data extraction unit 2a. The data pre-processing unit 2b processes the pre-processed roll phenomenon data to obtain pre-processed roll phenomenon data. For example, the data pre-processing unit 2b filters the pre-processed roll phenomenon data. For example, the filter may be a low-pass filter or a high-pass filter. The pre-processed roll phenomenon data and the pre-processed roll phenomenon data are collectively referred to as roll phenomenon data.

[0049] For example, the data quantification unit 3 is a PLC. For example, the data quantification unit 3 is a DCS. For example, the data quantification unit 3 is a general-purpose computer. The data quantification unit 3 receives pre-processed roll phenomenon data from the data acquisition unit 2. The data quantification unit 3 generates state quantification data based on the pre-processed roll phenomenon data. The state quantification data quantifies the state of the rolling rolls. The data quantification unit 3 transmits the state quantification data. The data quantification unit 3 includes a basic statistical quantity calculation unit 3a.

[0050] The basic statistics calculation unit 3a calculates basic statistics based on the pre-processed roll phenomenon data to be quantified, generating state quantitative data. Examples of basic statistics include the mean, median, difference between maximum and minimum values, standard deviation, and variance. The basic statistics calculation unit 3a generates state quantitative data for each type of roll phenomenon data. The basic statistics calculation unit 3a generates state quantitative data for each pre-rolled material 41 and each post-rolled material 42.

[0051] The data storage unit 4 is configured to communicate with the data quantification unit 3. The data storage unit 4 is also configured to communicate with the process computer 12. The data storage unit 4 receives state quantification data from the data quantification unit 3. The data storage unit 4 receives state quantification data from the data quantification unit 3 for each of the multiple rolling rolls. The data storage unit 4 stores the state quantification data. The data storage unit 4 accumulates and stores previously received state quantification data. The data storage unit 4 receives values ​​calculated by the process computer 12 and application condition data from the process computer 12. The data storage unit 4 includes a data storage unit 4a, a delamination phenomenon history data reading unit 4b, and a delamination phenomenon history database 4c. The data storage unit 4 generates delamination phenomenon history data based on the application condition data and the stored data. For example, delamination phenomenon history data is data that records, for each layer, items such as the roll ID, the bearing of the backup roll, manufacturing specifications such as the steel grade, size, and temperature of the rolled material, and rolling conditions. The roll ID is a number that individually identifies the rolling roll.

[0052] The data storage unit 4a, the layered phenomenon history data reading unit 4b, and the layered phenomenon history database 4c are provided so as to be able to communicate with each other.

[0053] The data storage unit 4a receives roll phenomenon data and state quantification data from the data quantification unit 3. The data storage unit 4a also receives application condition data related to the roll application from the process computer 12. For example, application condition data related to rolling rolls includes roll IDs, back-up roll bearings, manufacturing specifications such as the steel grade, size, and temperature of the rolled material, and rolling conditions. For example, the data storage unit 4a stores other application condition data using the roll ID as a key.

[0054] The layered phenomenon history data reading unit 4b reads the layered phenomenon history data in response to an external request. The layered phenomenon history data reading unit 4b receives a request from another device and reads the layered phenomenon history data. The layered phenomenon history data reading unit 4b receives a request from another device and reads the layered phenomenon history data with the same application condition data. The layered phenomenon history data reading unit 4b receives a request from another device and reads the layered phenomenon history data with similar application condition data. For example, the layered phenomenon history data reading unit 4b reads the layered phenomenon history data in response to a request from the process computer 12. The layered phenomenon history data is generated by indexing each layer using arbitrary items from the data stored in the layered phenomenon history database 4c, using the roller ID as a key, and from related data such as state quantification data and other related application conditions.

[0055] The hierarchical phenomenon history database 4c stores the data received by the data storage unit 4a and the acquisition time of each data in association with the hierarchical phenomenon history data.

[0056] The state determination unit 5 is configured to communicate with the data storage unit 4. The state determination unit 5 receives quantitative state data from the data storage unit 4. The state determination unit 5 reads delamination phenomenon history data from the data storage unit 4. The state determination unit 5 determines the state pattern of the rolling roll based on the quantitative state data and delamination phenomenon history data associated with application condition data that is identical or similar to the application condition data of the specific rolling roll used in the rolling process. The state determination unit 5 includes a state phenomenon database 5a and a state determination unit 5b.

[0057] The state phenomenon database 5a has a state judgment threshold database and a state pattern database. For example, the state judgment threshold database lists the state judgment thresholds used to judge whether the state is abnormal and the level of the state, i.e., the state level, for each state quantitative data. The state judgment threshold is a value used to judge whether the state of the roller is abnormal and the level of the state. For example, the state judgment threshold is preset. For example, the state judgment threshold is set semi-fixedly. For example, the state judgment threshold is calculated based on the user 7's past experience and knowledge of the device. For example, the state pattern is preset. For example, the state pattern is set semi-fixedly. For example, the state pattern is calculated based on the user 7's past experience and knowledge of the device.

[0058] Upon receiving application condition data for a specific rolling roll used in rolling, the state determination unit 5b reads delamination phenomenon history data associated with application condition data identical or similar to the application condition data from the data storage unit 4. For example, upon receiving the rolling roll ID and application conditions associated with the state quantification data, the state determination unit 5b reads delamination phenomenon history data associated with the rolling roll ID and application conditions from the data storage unit 4. For example, upon receiving the rolling roll ID and application conditions from the data storage unit 4, the state determination unit 5b reads delamination phenomenon history data associated with the rolling roll ID and application conditions from the data storage unit 4. The state determination unit 5b compares the read delamination phenomenon history data with data obtained from the state phenomenon database 5a to determine the state level and state pattern of the state quantification data. Based on the read delamination phenomenon history data and the state determination threshold value obtained from the state phenomenon database 5a, the state determination unit 5b determines whether the roll state is abnormal and the state level. The state determination unit 5b determines the state pattern for each combination of data item that conflicts with the state determination threshold value and the state level.

[0059] The recommended application method determination unit 6 is configured to be able to communicate with the data storage unit 4. The recommended application method determination unit 6 is configured to be able to communicate with the state determination unit 5. The recommended application method determination unit 6 receives, from the state determination unit 5, data items that conflict with the state determination threshold and the state pattern determined by the state determination unit 5. The recommended application method determination unit 6 determines the recommended application method and the delamination phenomenon history data of the rolling roll. The recommended application method determination unit 6 externally displays the recommended application method and the delamination phenomenon history data of the rolling roll. The recommended application method determination unit 6 presents the recommended application method and the delamination phenomenon history data of the rolling roll to the user 7. The recommended application method determination unit 6 has a recommended application method database 6a and a recommended application method determination unit 6b.

[0060] The recommended application method database 6a stores values ​​used to determine recommended application methods for rolling rolls. For example, the values ​​used to determine recommended application methods for rolling rolls are values ​​used to determine recommended application methods for a combination of state patterns. Recommended application methods are recommended application methods for rolling rolls based on the state patterns. For example, a recommended application method could be avoiding roll application due to roll replacement. For example, a recommended application method could be changing rolling conditions due to reducing roll load.

[0061] Upon receiving the rolling roll ID and application conditions, the recommended application method determination unit 6b obtains the status pattern from the status determination unit 5b, with respect to the delamination phenomenon history data associated with the rolling roll ID and application conditions and the delamination phenomenon history data. Based on the received status pattern, the recommended application method determination unit 6b obtains an appropriate recommended application method from the recommended application method database 6a. The recommended application method determination unit 6b externally displays the recommended application method and delamination phenomenon history data for the rolling roll. For example, the recommended application method determination unit 6b presents the recommended application method and delamination phenomenon history data to the user 7. For example, the recommended application method determination unit 6b presents the presentation to the user 7 via a display on a display device. For example, the recommended application method determination unit 6b presents the presentation to the user 7 via a voice output device.

[0062] Next, use Figure 3 An example of the processing performed by the data extraction unit 2a until the unrolled material 41 is rolled to the distance L after the start of rolling will be described.

[0063] Figure 3 This is a diagram showing an example of a roll physical quantity signal, a material entry detection signal, a material departure detection signal, and a material total length measurement signal of the roll management device according to the first embodiment.

[0064] The top graph shows the roller physical quantity signal. The second graph from the top shows the material entry detection signal. The third graph from the top shows the material separation detection signal. The bottom graph shows the material total length measurement signal.

[0065] Time T0 is the moment when the material is bitten by the upper rolling roll 21 and the lower rolling roll 22. Time T is the moment when the material is rolled by the length L. Time T1 is the moment when the rolled material 42 is rolled to the position L1 from the front end. Time T2 is the moment when the rolled material 42 is rolled to the position L2 from the front end.

[0066] For example, the data extraction unit 2a (not shown) extracts roll physical quantity signals within a time range based on the elapsed time since the start of rolling. Specifically, by setting the extraction time range to be from time T0 to time T, the data extraction unit 2a collects roll phenomenon data related to the upper rolling roll 21 from the start of rolling until the rolling distance L has been covered. By setting the extraction time range to be from time T0 to time T1, the data extraction unit 2a collects roll phenomenon data related to the upper rolling roll 21 from the start of rolling until the rolling distance L1 has been covered.

[0067] For example, the data extraction unit 2a collects roller phenomenon data from appropriate locations within the rolled material 42 during rolling. Specifically, the data extraction unit 2a uses the total material length measurement signal as the timing corresponding to the time range from the middle portion L1 to L2 of the rolled material 42, thereby obtaining the time range from time T1 to time T2. The data extraction unit 2a extracts the roller physical quantity signal within the time range from time T1 to time T2. As a result, the data extraction unit 2a collects roller phenomenon data during rolling of the portion L1 to L2 of the rolled material 42.

[0068] Next, use Figure 4 An example of processing the pre-roll phenomenon data and pre-processing the post-roll phenomenon data will be described.

[0069] Figure 4 This is a graph showing examples of pre-processing roll phenomenon data and post-processing roll phenomenon data in the roll management device according to the first embodiment.

[0070] Figure 4 The upper graph is a graph showing pre-processing roll phenomenon data related to the vibration of the rolling roll collected by the data extraction unit 2a. Figure 4 The lower graph is a graph showing the roller phenomenon data after the pre-processing process of the data pre-processing unit 2b. Figure 4 As shown, the pre-processed rolling phenomenon data contains noise. This noise includes transient noise and low-frequency noise with large fluctuations. The post-processed rolling phenomenon data is filtered to remove the noise.

[0071] Next, use Figure 5 An example of a hierarchical phenomenon history database will be described.

[0072] Figure 5 This is a diagram showing an example of a delamination phenomenon history database of the roll management device according to the first embodiment.

[0073] like Figure 5 As shown, the delamination history data records items such as the rolling material ID, roll ID, inspection ID, rolling material type, rolling material dimensions, rolling conditions, data acquisition time, and state quantitative data. For example, the delamination history data is divided into data records 1, 2, and 3 based on the data acquisition time, and data is recorded for each item for each layer.

[0074] Next, use Figure 6 An example of a state determination threshold database will be described.

[0075] Figure 6 This is a diagram showing an example of the state determination threshold database of the roll management device according to the first embodiment.

[0076] like Figure 6 As shown in FIG, in the state judgment threshold database, multiple state judgment thresholds are set for the state quantitative data. Figure 6 In the example shown, regarding the state quantification data A, in the case of the threshold value X1, the state level is "level 1".

[0077] Next, use Figure 7 Illustrate an example of a state schema database.

[0078] Figure 7 This is a diagram showing an example of a status pattern database of the roll management device according to the first embodiment.

[0079] like Figure 7 As shown, in the state pattern database, the state pattern to be judged is set according to the combination of the data items that conflict with the state judgment threshold and their state levels. Figure 7 In the example shown, when the data item that conflicts with the state judgment threshold is state quantification data A and the state level is 2, and when the data item that conflicts with the state judgment threshold is state quantification data B and the state level is 2, the state pattern is judged as "having the possibility of state pattern X".

[0080] Next, use Figure 8 An example of a database of recommended application methods is described.

[0081] Figure 8 This is a diagram showing an example of the recommended application method database of the roll management device according to the first embodiment.

[0082] like Figure 8 As shown in FIG, in the recommended application method database, the recommended application method is set for the determined state mode. Figure 9 In the example shown, when it is determined that there is a possibility of the state pattern X, the recommended application method is "load reduction".

[0083] Next, use Figure 9 The operation of the roll management device 1 will be described.

[0084] Figure 9 This is a flowchart for explaining an outline of the operation of the roll management device according to the first embodiment.

[0085] In step S1, the rolling mill 11 starts rolling the material. Then, the data collection unit 2 performs the operation of step S2.

[0086] In step S2, the data collecting unit 2 collects roller phenomenon data. Then, the data quantifying unit 3 performs the operation of step S3.

[0087] In step S3, the data quantification unit 3 generates state quantification data. Then, the data storage unit 4 performs the operation of step S4.

[0088] In step S4, the data storage unit 4 stores the state quantification data. Then, the data storage unit 4 reads the delamination phenomenon history data based on the input from the process computer 12. Then, the state determination unit 5 performs the operation of step S5.

[0089] In step S5, the state determination unit 5 determines the state pattern of the rolling roll based on the delamination phenomenon history data. Then, the recommended application method determination unit 6 performs the operation of step S6.

[0090] In step S6, the recommended application method determination unit 6 determines the recommended application method based on the state pattern. Then, the roll management device 1 performs the operation of step S7.

[0091] In step S7, the roll management device 1 displays the recommended application method externally. Then, the roll management device 1 ends the process.

[0092] Next, use Figure 10 An example of the roll management device 1 will be described.

[0093] Figure 10 This is a hardware configuration diagram of the roll management device according to the first embodiment.

[0094] Each function of the roller management device 1 can be implemented by a processing circuit. For example, the processing circuit has at least one processor 100 a and at least one memory 100 b. For example, the processing circuit has at least one dedicated hardware 200 .

[0095] When the processing circuit includes at least one processor 100a and at least one memory 100b, the various functions of the roll management device 1 are implemented using software, firmware, or a combination of software and firmware. At least one of the software and firmware is described as a program. At least one of the software and firmware is stored in the at least one memory 100b. The at least one processor 100a implements the various functions of the roll management device 1 by reading and executing the program stored in the at least one memory 100b. The at least one processor 100a is also referred to as a central processing unit, processing unit, computing unit, microprocessor, microcomputer, or DSP. For example, the at least one memory 100b may be a non-volatile or volatile semiconductor memory such as RAM, ROM, flash memory, EPROM, or EEPROM, or a magnetic disk, floppy disk, optical disk, CD, minidisc, or DVD.

[0096] When the processing circuit comprises at least one dedicated hardware component 200, the processing circuit may be implemented, for example, as a single circuit, a composite circuit, a programmable processor, a parallel programmable processor, an ASIC, an FPGA, or a combination thereof. For example, each function of the monitoring device 9 may be implemented separately by the processing circuit. For example, each function of the roll management device 1 may be implemented collectively by the processing circuit.

[0097] The various functions of the roll management device 1 may be partially implemented by dedicated hardware 200 and partially implemented by software or firmware. For example, the functions of the data acquisition unit 2 may be implemented by a processing circuit as dedicated hardware 200, while functions other than the data acquisition unit 2 may be implemented by at least one processor 100a reading and executing a program stored in at least one memory 100b.

[0098] In this way, the processing circuit can realize each function of the roller management device 1 through hardware 200, software, firmware, or a combination thereof.

[0099] According to the first embodiment described above, the roll management device 1 presents a recommended application method for a specific rolling roll based on the state of the specific rolling roll. Therefore, the rolling roll can be appropriately applied.

[0100] Furthermore, the roll management device 1 can suppress abnormalities of the rolling rolls, thereby enabling planned production of rolled materials.

[0101] Furthermore, the roll management device 1 can suppress the breakage of the rolling rolls, thereby reducing the influence of a failure of the rolling mill on equipment other than the rolling mill.

[0102] Furthermore, the roll management device 1 automatically quantifies the data, so the user 7 does not need to perform the work of quantifying the data.

[0103] Furthermore, the roll management device 1 records a plurality of data related to rolling. Therefore, there is no need to integrate the plurality of data related to rolling.

[0104] Furthermore, the roll management device 1 presents the recommended application method of the rolling roll and the delamination phenomenon history data to the user 7. Therefore, the user 7 can determine how to use the rolling rolls used in the rolling mill 11 for rolling based on his or her own experience and knowledge.

[0105] Furthermore, the roll management device 1 includes a state determination threshold database, thereby improving the determination accuracy for each rolling position.

[0106] Furthermore, the roller management device 1 quantifies the roller phenomenon data and generates state quantification data, thereby being able to quantitatively grasp the roller state.

[0107] Furthermore, the roll management device 1 only collects data at the required timeframe. This reduces the amount of data collected. This shortens data processing time, reduces computational load, and improves processing accuracy. This allows pre-processing roll phenomenon data to be processed using a general-purpose computer.

[0108] Furthermore, the roll management device 1 collects pre-processing roll phenomenon data at an appropriate sampling cycle. This reduces the amount of collected data. This results in shorter data processing time, lowered computational load, and improved processing accuracy. This allows pre-processing roll phenomenon data to be processed using a general-purpose computer.

[0109] Furthermore, the roll management device 1 collects all pre-processing roll phenomenon data within an appropriate sampling time range, so that the pre-processing roll phenomenon data can be processed using a general-purpose computer.

[0110] Furthermore, the roll management device 1 sets the front end, the middle, and the rear end of the total length of the material as appropriate sampling time ranges, thereby improving the determination accuracy for each rolling position.

[0111] Furthermore, the roll management device 1 may not include the data quantification unit 3. In this case, the data storage unit 4 receives the pre-processed roll phenomenon data from the data acquisition unit 2. Consequently, the roll management device 1 determines the recommended application method for the rolling roll based on the pre-processed roll phenomenon data.

[0112] In the description of the first embodiment, a method in which the data extracting unit 2a collects data at a timing corresponding to a necessary time range is exemplified. However, other means capable of obtaining appropriate timing may be used instead.

[0113] Furthermore, the roller management device 1 generates post-processing roller phenomenon data by applying a filter to the pre-processing roller phenomenon data, thereby shortening the data processing time, reducing the calculation load, and improving the processing accuracy.

[0114] In addition, in the pre-processing performed by the data acquisition unit on the pre-processing roller phenomenon data, data cleaning such as supplementation of missing data or normalization of different data formats can also be performed.

[0115] In addition, the roller management device 1 may not perform filtering processing and data cleaning on the pre-processing roller phenomenon data.

[0116] In addition, the data quantification unit 3 and the data acquisition unit 2 may be integrated.

[0117] Furthermore, although the upper rolling roll 21 is described as the object of management, the lower rolling roll 22 may also be the object of management. In this case, the roll physical quantity sensor 31 only needs to measure the physical quantity related to the lower rolling roll 22.

[0118] In addition, although the upper rolling roll 21 is described as the object of management, both the upper rolling roll 21 and the lower rolling roll 22 may be managed. In this case, the roll physical quantity sensor 31 only needs to measure the physical quantities related to the upper rolling roll 21 and the lower rolling roll 22.

[0119] Furthermore, when the recommended application method determination unit 6 b reads data related to the application conditions acquired for determination of the recommended application method from the data storage unit 4 , it may read data matching all data items constituting the application conditions.

[0120] Furthermore, when the recommended application method determination unit 6 b reads data related to the application conditions acquired for determination of the recommended application method from the data storage unit 4 , it may read data in which some of the data items match.

[0121] Implementation Method 2

[0122] Figure 11 2 is a block diagram of a roll management device according to Embodiment 2. Components identical or corresponding to those in Embodiment 1 are given the same reference numerals, and descriptions of such components are omitted.

[0123] The data quantification unit 3 in the second embodiment includes a frequency analysis unit 3 b .

[0124] The frequency analysis unit 3b performs frequency analysis on the pre-processed roller phenomenon data, which is the target of data quantification, and converts it into frequency-domain data, such as the signal intensity of each frequency component. The frequency analysis unit 3b generates state quantification data based on the converted frequency-domain data. For example, frequency analysis involves known analysis methods such as Fourier transform, discrete Fourier transform, and wavelet transform, which convert roller phenomenon data expressed in the time domain into frequency-domain data, such as the signal intensity of each frequency component.

[0125] According to the second embodiment described above, state quantitative data can be generated that quantifies the amount of each frequency component contained in the roller phenomenon data. This increases the variety of state quantitative data items used for state determination. Consequently, the accuracy of state pattern determination can be improved. Furthermore, useful recommended usage methods and judgment-based data can be presented to the user 7.

[0126] Implementation 3

[0127] Figure 123 is a block diagram of a roll management device according to Embodiment 3. Components identical or corresponding to those in Embodiment 2 are given the same reference numerals, and their descriptions are omitted.

[0128] The quantification unit 3 in this third embodiment includes a data model estimation unit 3c. The data model estimation unit 3c analyzes the pre-processed roller phenomenon data, which is the target of data quantification, based on a data model and generates state quantification data. The data model is a known model such as a probability density function model, an autoregressive model, or a neural network model.

[0129] According to the third embodiment described above, data model parameters can be used as a quantitative means. This increases the variety of state quantitative data items used for state determination. Consequently, the accuracy of state pattern determination can be improved. Furthermore, useful recommended usage methods and judgment-based data can be presented to the user 7.

[0130] In addition, the data quantification unit 3 of the present embodiment 3 does not need to include the frequency analysis unit 3 b.

[0131] Implementation 4

[0132] Figure 13 1 is a block diagram of a roll management device according to Embodiment 4. Components identical or corresponding to those in Embodiment 3 are given the same reference numerals, and their descriptions are omitted.

[0133] The data quantification unit 3 of the present embodiment 4 has a manual input unit 3d for quantitative data. The manual input unit 3d for quantitative data accepts input of data that has been quantified externally. For example, data that has been quantified externally refers to data that has been quantified by the user 7 based on his or her own experience and knowledge. Specifically, data that has been quantified externally refers to data based on phenomena discovered by the operator. For example, data based on phenomena discovered by the operator include rolling instability phenomena such as meandering and lateral misalignment of the material that occur during rolling, rolling failure events such as defects in the product and poor shape of the product, collision between the material and the rolling roll, state vibration of the rolling roll, overload of the rolling roll, and defects in the rolling roll, or the number of occurrences, evaluation points, or the number of occurrences and evaluation points of the rolling equipment.

[0134] According to the fourth embodiment described above, externally quantified data is accepted. Therefore, the types of state quantitative data items used for state determination can be increased. Consequently, the accuracy of state pattern determination can be improved. Furthermore, useful recommended usage methods and judgment-based data can be presented to the user 7.

[0135] In addition, the quantification unit 3 of the fourth embodiment does not need to include the frequency analysis unit 3 b.

[0136] In addition, the quantification unit 3 of the present fourth embodiment does not need to include the data model estimation unit 3 c.

[0137] Implementation 5

[0138] Figure 14 1 is a block diagram of a roll management device according to Embodiment 5. Components identical or corresponding to those in Embodiment 1 are given the same reference numerals, and their descriptions are omitted.

[0139] The state determination unit 5 of the fifth embodiment includes a state determination threshold value calculation unit 5c.

[0140] The state determination threshold calculation unit 5c dynamically calculates the state determination threshold based on the state quantitative data. The state determination threshold calculation unit 5c sets the calculated state determination threshold. For example, upon obtaining the rolling roll ID and application conditions, the state determination threshold calculation unit 5c applies a method for calculating the state determination threshold, such as Hotelling's theory, to the state quantitative data associated with the rolling roll ID. As a result, the state determination threshold calculation unit 5c dynamically calculates the state determination threshold.

[0141] According to the fifth embodiment described above, the state determination threshold value is dynamically calculated by the state determination threshold value calculation unit 5c. Therefore, when an unexpected situation occurs, the state determination unit 5 can adjust the state determination threshold value accordingly. As a result, the accuracy of determining the state pattern can be improved. Furthermore, useful recommended usage methods and judgment basis data can be presented to the user 7.

[0142] Implementation Method 6

[0143] Figure 15 1 is a block diagram of a roll management device according to Embodiment 6. Components identical or corresponding to those in Embodiment 5 are given the same reference numerals, and descriptions of such components are omitted.

[0144] The state determination unit 5 of the sixth embodiment includes a state determination logic estimation unit 5d.

[0145] The state judgment logic inference unit 5d constructs a causal relationship model based on the rolling roll ID, delamination phenomenon history data, and application condition data. The state judgment logic inference unit 5d compares the constructed causal relationship model with the application condition data during rolling and sets the logic for determining the state mode. For example, the causal relationship model can be a statistical causal relationship model, a deterministic tree, a neural network, or other non-statistical causal relationship model. Based on the causal relationship model, the state judgment logic inference unit 5d sets the logic for determining the state mode for the combination of data items that conflict with the state judgment threshold and their state level. The state judgment unit 5 determines the state mode based on this logic.

[0146] According to the sixth embodiment described above, the state determination unit 5 determines the state pattern based on this logic. This improves the accuracy of determining the state pattern and provides the user 7 with useful recommended usage methods and judgment basis data.

[0147] In addition, the state determination unit 5 of the sixth embodiment does not need to include the state determination threshold calculation unit 5 c.

[0148] Modification

[0149] The roll management device 1 of the modified example has the same configuration as the roll management device 1 of the first embodiment.

[0150] The recommended application method determination unit 6 b of the seventh embodiment can estimate the recommended application method of the application condition of the rolling roll ID based on the state pattern of the same application condition related to other rolling roll IDs.

[0151] When the recommended application method determination unit 6b obtains a certain rolling roll ID and application conditions, regardless of the rolling roll ID, it uses the application conditions as a key to obtain the stratification phenomenon history data related to the application conditions, and the state pattern determined by the state determination device by processing the stratification phenomenon history data.

[0152] For example, upon obtaining a particular rolling roll ID and application conditions, the recommended application method determination unit 6b obtains delamination phenomenon history data corresponding to the application conditions, regardless of the rolling roll ID, and the state pattern determined by the state determination device through processing of the delamination phenomenon history data. Specifically, when a particular rolling roll is rolling a soft and wide material, the recommended application method determination unit 6b obtains delamination phenomenon history data for other rolling rolls rolling a soft and wide material, and the state pattern determined by the state determination device through processing of the delamination phenomenon history data.

[0153] For example, upon obtaining a specific rolling roll ID and application conditions, the recommended application method determination unit 6b obtains delamination phenomenon history data similar to the application conditions, regardless of the rolling roll ID, and the state pattern determined by the state determination device through processing of the delamination phenomenon history data. Specifically, when a specific rolling roll is rolling a soft and wide material, the recommended application method determination unit 6b obtains delamination phenomenon history data for the case of rolling a wide material, regardless of the hardness of the material associated with the other rolling rolls, and the state pattern determined by processing of the delamination phenomenon history data by the state determination device.

[0154] According to the modified example described above, the recommended application method determination unit 6b obtains the status pattern regardless of the rolling roll ID. Therefore, the roll management device 1 can determine the recommended application method based on data related to the same rolling conditions. As a result, the roll management device 1 can perform a wide range of determinations, improving determination accuracy.

[0155] Implementation 7

[0156] Figure 16 1 is a block diagram of a roll management device according to Embodiment 7. Components identical or corresponding to those in Embodiment 1 are given the same reference numerals, and their descriptions are omitted.

[0157] The state determination unit 5 of the eighth embodiment includes a state occurrence prediction unit 5e.

[0158] The state occurrence prediction unit 5e transmits state pattern data based on inferences derived from existing knowledge to the recommended application method determination unit 6. Specifically, if the inferences derived from existing knowledge include the following: for a certain state pattern P, if a state pattern is generated under application condition A for a certain rolling roll ID: X, then the same state pattern may also be generated under a different rolling roll ID: Y and application condition: B. This operation involves transmitting data on an estimated state pattern that may be generated by state pattern P to the recommended application method determination unit 6, if the recommended application method determination unit 6 wishes to obtain a state pattern associated with rolling roll ID: Y and application condition: B, when state pattern P is generated under rolling roll ID: X and application condition: A.

[0159] According to the seventh embodiment described above, the roll management device 1 determines a recommended application method based on inference using prior knowledge representing inference. Therefore, for a certain rolling roll ID and a certain application condition, even if a state pattern could not be determined in the past, a recommended application method can be determined.

Claims

1. A roller management device comprising: A data acquisition unit that collects physical quantities related to a plurality of rolling rolls during rolling and data on rolling application conditions; a data storage unit for accumulating physical quantities and rolling application condition data collected by the data collection unit up to the previous rolling; A state determination unit reads relevant physical quantities of rolling application condition data that is identical or similar to rolling application condition data of a specific rolling roll used for rolling and stored in the data storage unit, and determines the state of the specific rolling roll based on the relevant physical quantities; as well as a recommended application method determination unit that presents a recommended application method for the specific rolling roll based on the state of the specific rolling roll determined by the state determination unit, The roller management device further comprises: a data quantification unit that generates state quantification data by quantifying the physical quantity; The data storage unit accumulates the state quantitative data generated by the data quantification unit, The state determination unit includes: a state determination threshold database recording a plurality of state determination thresholds, wherein the plurality of state determination thresholds are thresholds for determining a plurality of state levels of the specific rolling roll for respective pieces of state quantitative data; as well as A state pattern database records a plurality of state patterns, wherein the plurality of state patterns are set for combinations of state quantitative data and state levels that conflict with a state determination threshold value. Determine the state mode based on the state quantification data generated by the data quantification unit and its state level, The recommended application method determination unit includes: a recommended application method database, wherein the recommended application method is to replace the specific rolling roll and reduce the load of the specific rolling roll in response to the determined state pattern; Based on the state pattern determined by the state determination unit, one selected from replacement of the specific rolling roll and reduction of the load on the specific rolling roll is suggested as the application method.

2. The roller management device according to claim 1, The state determination unit reads relevant physical quantities for the application condition data of rolling related to the specific rolling roller accumulated in the data storage unit, which is the same as or similar to the application condition data of rolling of the specific rolling roller, and determines the state of the specific rolling roller based on the relevant physical quantities.

3. The roller management device according to claim 1, The state determination unit reads relevant physical quantities of the application condition data on rolling related to other rolling rolls accumulated in the data storage unit that are the same or similar to the application condition data on rolling of the specific rolling roll, and determines the state of the specific rolling roll based on the relevant physical quantities.

4. The roller management device according to any one of claims 1 to 3, The data acquisition unit acquires the physical quantity according to a preset sampling period.

5. The roller management device according to any one of claims 1 to 3, The data acquisition unit acquires physical quantities according to a preset sampling time range.

6. The roller management device according to any one of claims 1 to 3, The data collection unit performs filtering or cleaning on the collected physical quantities related to the plurality of rolling rolls during rolling.

7. The roller management device according to any one of claims 1 to 3, The data storage unit accumulates a plurality of physical quantities and a plurality of rolling application condition data in a time series order and in each layer for each material to be rolled. The status determination unit reads relevant physical quantities for the application condition data of rolling associated with the roller ID of the specific rolling roller accumulated in the data storage unit, which is the same as or similar to the application condition data of rolling of the specific rolling roller, and determines the status of the specific rolling roller based on the relevant physical quantities.

8. The roller management device according to any one of claims 1 to 3, The data storage unit accumulates a plurality of physical quantities and a plurality of rolling application condition data in a time series order and in each layer for each material to be rolled. The state determination unit constructs a cause-effect relationship model for the plurality of physical quantities and the plurality of rolling application condition data accumulated in the data storage unit. The state of the specific rolling roll is determined by comparing the rolling application condition data of the specific rolling roll with the causal relationship model.

9. The roller management device according to any one of claims 1 to 3, The state determination unit reads relevant state quantification data for the rolling application condition data that is identical or similar to the rolling application condition data of the specific rolling roller accumulated in the data storage unit, and determines the state of the specific rolling roller based on the relevant state quantification data.

10. The roller management device according to claim 9, The data quantification unit quantifies the physical quantity based on basic statistics and generates state quantification data.

11. The roller management device according to claim 9, The data quantification unit quantifies the physical quantity based on frequency analysis and generates state quantification data.

12. The roller management device according to claim 9, The data quantification unit analyzes the physical quantity according to a data model and generates state quantification data.

13. The roller management device according to claim 1, The state determination unit dynamically calculates the threshold value.

14. The roller management device according to claim 9, The state determination unit determines the state level of the rolling roll when it is used based on the state quantification data associated with the rolling application condition data accumulated in the data storage unit for the roll ID identical to the roll ID of the specific rolling roll. The recommended application method determination unit determines an application method recommended for the specific rolling roll based on the state level determined by the state determination unit.

15. The roller management device according to claim 9, The state determination unit determines the state of the specific rolling roll based on state quantification data input from the outside.

16. The roller management device according to any one of claims 1 to 3, The state determination unit determines the state of the specific rolling roll based on inference using existing knowledge.

Images