WO2022049975A1 - 圧延機の振動予測方法、圧延機の異常振動判定方法、金属帯の圧延方法、及び圧延機の振動予測モデルの生成方法 - Google Patents
圧延機の振動予測方法、圧延機の異常振動判定方法、金属帯の圧延方法、及び圧延機の振動予測モデルの生成方法 Download PDFInfo
- Publication number
- WO2022049975A1 WO2022049975A1 PCT/JP2021/028936 JP2021028936W WO2022049975A1 WO 2022049975 A1 WO2022049975 A1 WO 2022049975A1 JP 2021028936 W JP2021028936 W JP 2021028936W WO 2022049975 A1 WO2022049975 A1 WO 2022049975A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- rolling
- vibration
- rolling mill
- roll
- grinding
- Prior art date
Links
- 238000005096 rolling process Methods 0.000 title claims abstract description 486
- 238000000034 method Methods 0.000 title claims abstract description 93
- 239000002184 metal Substances 0.000 title claims abstract description 54
- 230000002159 abnormal effect Effects 0.000 title claims description 37
- 238000010801 machine learning Methods 0.000 claims abstract description 21
- 238000013528 artificial neural network Methods 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 4
- 238000003066 decision tree Methods 0.000 claims description 3
- 238000007637 random forest analysis Methods 0.000 claims description 3
- 238000005498 polishing Methods 0.000 abstract 1
- 229910000831 Steel Inorganic materials 0.000 description 39
- 239000010959 steel Substances 0.000 description 39
- 230000001133 acceleration Effects 0.000 description 38
- 238000005097 cold rolling Methods 0.000 description 34
- 230000008569 process Effects 0.000 description 33
- 238000012545 processing Methods 0.000 description 33
- 230000003595 spectral effect Effects 0.000 description 31
- 244000145845 chattering Species 0.000 description 21
- 238000004364 calculation method Methods 0.000 description 15
- 238000004519 manufacturing process Methods 0.000 description 15
- 238000004458 analytical method Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 12
- 238000005520 cutting process Methods 0.000 description 10
- 238000006073 displacement reaction Methods 0.000 description 10
- 238000005070 sampling Methods 0.000 description 9
- 230000000052 comparative effect Effects 0.000 description 6
- 230000007547 defect Effects 0.000 description 6
- 230000002093 peripheral effect Effects 0.000 description 6
- 238000007747 plating Methods 0.000 description 6
- 238000012935 Averaging Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 239000000463 material Substances 0.000 description 5
- 230000003746 surface roughness Effects 0.000 description 4
- 239000006061 abrasive grain Substances 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 230000000737 periodic effect Effects 0.000 description 3
- 230000009467 reduction Effects 0.000 description 3
- 238000001228 spectrum Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 238000003466 welding Methods 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- PNEYBMLMFCGWSK-UHFFFAOYSA-N aluminium oxide Inorganic materials [O-2].[O-2].[O-2].[Al+3].[Al+3] PNEYBMLMFCGWSK-UHFFFAOYSA-N 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 230000006866 deterioration Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000011144 upstream manufacturing Methods 0.000 description 2
- 238000011179 visual inspection Methods 0.000 description 2
- 229910001209 Low-carbon steel Inorganic materials 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 238000000137 annealing Methods 0.000 description 1
- 239000010953 base metal Substances 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 235000013361 beverage Nutrition 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000009749 continuous casting Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 229910003460 diamond Inorganic materials 0.000 description 1
- 239000010432 diamond Substances 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005098 hot rolling Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- NJPPVKZQTLUDBO-UHFFFAOYSA-N novaluron Chemical compound C1=C(Cl)C(OC(F)(F)C(OC(F)(F)F)F)=CC=C1NC(=O)NC(=O)C1=C(F)C=CC=C1F NJPPVKZQTLUDBO-UHFFFAOYSA-N 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 239000004575 stone Substances 0.000 description 1
- 238000004381 surface treatment Methods 0.000 description 1
- 230000002459 sustained effect Effects 0.000 description 1
- 239000013077 target material Substances 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000004804 winding Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B21—MECHANICAL METAL-WORKING WITHOUT ESSENTIALLY REMOVING MATERIAL; PUNCHING METAL
- B21B—ROLLING OF METAL
- B21B33/00—Safety devices not otherwise provided for; Breaker blocks; Devices for freeing jammed rolls for handling cobbles; Overload safety devices
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B21—MECHANICAL METAL-WORKING WITHOUT ESSENTIALLY REMOVING MATERIAL; PUNCHING METAL
- B21B—ROLLING OF METAL
- B21B38/00—Methods or devices for measuring, detecting or monitoring specially adapted for metal-rolling mills, e.g. position detection, inspection of the product
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B21—MECHANICAL METAL-WORKING WITHOUT ESSENTIALLY REMOVING MATERIAL; PUNCHING METAL
- B21C—MANUFACTURE OF METAL SHEETS, WIRE, RODS, TUBES OR PROFILES, OTHERWISE THAN BY ROLLING; AUXILIARY OPERATIONS USED IN CONNECTION WITH METAL-WORKING WITHOUT ESSENTIALLY REMOVING MATERIAL
- B21C51/00—Measuring, gauging, indicating, counting, or marking devices specially adapted for use in the production or manipulation of material in accordance with subclasses B21B - B21F
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B24—GRINDING; POLISHING
- B24B—MACHINES, DEVICES, OR PROCESSES FOR GRINDING OR POLISHING; DRESSING OR CONDITIONING OF ABRADING SURFACES; FEEDING OF GRINDING, POLISHING, OR LAPPING AGENTS
- B24B5/00—Machines or devices designed for grinding surfaces of revolution on work, including those which also grind adjacent plane surfaces; Accessories therefor
- B24B5/36—Single-purpose machines or devices
- B24B5/37—Single-purpose machines or devices for grinding rolls, e.g. barrel-shaped rolls
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Definitions
- the present invention relates to a method for predicting vibration of a rolling mill, a method for determining abnormal vibration of a rolling mill, a method for rolling a metal strip, and a method for generating a vibration prediction model for a rolling mill.
- Metal strips such as steel plates used for automobiles and beverage cans are subjected to a continuous casting process, a hot rolling process, and a cold rolling process, and then subjected to an annealing process and a plating process to become a product.
- the cold rolling process is the final process for determining the thickness of the metal strip as a product.
- the plating thickness may be thinner than before, and the surface texture of the metal strip before the plating process tends to affect the surface texture of the product after the plating process, so it is necessary to prevent the occurrence of surface defects. It is increasing.
- Chatter mark is one of the surface defects that occur in the cold rolling process. This is a linear mark that appears in the width direction of the metal band, and is a surface defect in which such a linear mark periodically appears in the longitudinal direction of the metal band.
- the chatter mark is said to be generated by the vibration of the rolling mill (hereinafter referred to as chattering).
- Very mild chatter marks cannot be found by visual inspection or plate thickness measurement after the cold rolling process, but may be found only after the plating process. For this reason, it is not noticed that a large amount of surface defects are generated during that time, and as a result, the yield of the product is lowered, which is a factor that greatly impairs the productivity.
- problems such as breakage of the metal strip may occur due to sudden fluctuations in the thickness and tension of the metal strip due to chattering, which may hinder productivity.
- chattering the vibration of the rolling mill
- Patent Document 1 a vibration detector is attached to a rolling mill, vibration information is collected during rolling, rolling operation parameters such as rolling load and tension between stands are acquired, and chattering is performed by analyzing their frequencies. A method for determining the occurrence of is described. Further, in Patent Document 1, the natural frequency of the rolling mill and the natural vibration frequency due to bearing failure or roll defect are identified in advance, and the cause of chatter mark is specified by comparing with the vibration information during rolling. How to do it is described.
- Patent Documents 2 and 3 a vibration detector is provided not only on the rolling mill body but also on a roll (small diameter roll) which is arranged between stands and on the entry / exit side of a tandem rolling mill and around which a metal band is wound at a certain angle or more. How to install is described. Further, in Patent Documents 2 and 3, frequency analysis of vibration information obtained by a vibration detector is performed, and chattering is performed when the vibration intensity exceeds a predetermined threshold at a frequency corresponding to the string vibration frequency of the metal band. The method of determining that is described. Further, Patent Documents 2 and 3 describe a method of controlling the string vibration frequency so as not to match the fundamental frequency of the rolling mill by controlling the tension between the stands.
- the present invention has been made in view of the above problems, and an object of the present invention is to provide a method for predicting vibration of a rolling mill that can predict the vibration of the rolling mill before rolling a metal strip. Another object of the present invention is to provide a method for determining abnormal vibration of a rolling mill that can predict abnormal vibration of the rolling mill before rolling a metal strip. Another object of the present invention is to provide a method for rolling a metal strip, which can suppress the generation of chatter marks and improve the manufacturing yield of the metal strip. Another object of the present invention is to provide a method for generating a vibration prediction model of a rolling mill capable of generating a vibration prediction model of a rolling mill that predicts the vibration of a rolling mill before rolling a metal strip.
- the method for predicting vibration of a rolling mill is a method for predicting vibration of a rolling mill that predicts the vibration of the rolling mill in a rolling process in which a metal strip is rolled by a rolling mill using a rolling roll ground by a roll grinder. Therefore, the input data includes one or more parameters selected from the grinding operation parameters of the roll grinder and one or two or more parameters selected from the rolling operation parameters of the rolling mill, and is included in the rolling process. It includes a step of predicting the vibration of the rolling mill using a rolling mill vibration prediction model learned by machine learning using the rolling mill vibration information as output data.
- the grinding operation parameter may include vibration information of the roll grinder acquired when the rolling roll is ground by the roll grinder.
- the grinding operation parameter may include a grinding wheel load parameter relating to load information on the grinding wheel when the rolling roll is ground by the roll grinder and a grinding wheel usage history parameter relating to usage history information of the grinding wheel.
- the method for determining abnormal vibration of the rolling mill according to the present invention is after the rolling roll ground by the roll grinder is incorporated into the rolling mill by using the vibration prediction method for the rolling mill according to the present invention, and the metal strip is formed.
- the vibration of the rolling mill when rolling the metal strip is predicted by using the actual value of the grinding operation parameter of the roll grinder and the set value of the rolling operation parameter of the rolling mill.
- the first step and the second step of determining whether or not abnormal vibration of the rolling mill is generated based on the comparison between the prediction result of the vibration by the first step and the preset upper limit value of the rolling mill vibration. ,including.
- the method for rolling a metal strip according to the present invention resets the rolling operation conditions of the rolling mill when it is determined that abnormal vibration of the rolling mill is generated by using the method for determining abnormal vibration of the rolling mill according to the present invention. Including steps.
- the method for generating the vibration prediction model of the rolling mill according to the present invention is the vibration of the rolling mill that predicts the vibration of the rolling mill in the rolling process of rolling a metal strip by the rolling mill using the rolling rolls ground by the roll grinder.
- a method for generating a rolling mill vibration prediction model for generating a prediction model in which actual data selected from the grinding operation parameters of the roll grinder and actual data selected from the rolling operation parameters of the rolling mill are input.
- machine learning it is preferable to use machine learning selected from neural networks, decision tree learning, random forest, and support vector regression.
- the present invention it is possible to provide a method for predicting vibration of a rolling mill that can predict the vibration of the rolling mill before rolling the metal strip. Further, according to the present invention, it is possible to provide a method for determining abnormal vibration of a rolling mill that can predict abnormal vibration of the rolling mill before rolling the metal strip. Further, according to the present invention, it is possible to provide a method for rolling a metal strip, which can suppress the generation of chatter marks and improve the manufacturing yield of the metal strip. Further, according to the present invention, it is possible to provide a method for generating a vibration prediction model of a rolling mill capable of generating a vibration prediction model of a rolling mill that predicts the vibration of the rolling mill before rolling a metal strip.
- FIG. 1 is a diagram showing a configuration of a rolling mill according to an embodiment of the present invention.
- FIG. 2 is a diagram showing a configuration of a roll grinder according to an embodiment of the present invention.
- FIG. 3 is a diagram showing a processing flow in the vibration signal processing unit of the roll grinder.
- FIG. 4 is a diagram showing a processing flow in the vibration signal processing unit of the rolling mill.
- FIG. 5 is a diagram for explaining a frequency band of interest as vibration information of a rolling mill.
- FIG. 6 is a diagram showing a configuration of a vibration prediction model generation unit.
- FIG. 7 is a diagram showing a processing flow in the vibration prediction model generation unit.
- FIG. 8 is a diagram showing a processing flow in the rolling mill vibration prediction unit.
- FIG. 9 is a diagram for explaining a method of acquiring vibration information of the roll grinder.
- chattering The abnormal vibration of the rolling mill in the cold rolling process of the metal strip is called chattering, and the periodic pattern formed on the surface of the metal strip by chattering is called the chatter mark.
- the chatter mark in which the surface of the metal band has irregularities having an amplitude of about 0.5 to 10 ⁇ m is treated. This often occurs because the thickness of the metal strip fluctuates. Chatter marks on which such minute irregularities on the surface are formed are often difficult to detect with a plate thickness gauge installed on the outlet side of the cold rolling mill. Further, it is difficult to determine even if the surface of the metal strip after cold rolling is visually observed. Such mild chatter marks are often detected after surface treatment such as plating, or for the first time after press forming of a metal strip.
- chattering which causes chatter marks
- chattering can be detected when the magnitude of vibration in a specific frequency band exceeds a preset threshold by analyzing vibration data acquired from a vibration meter installed in a rolling mill.
- the inventors of the present invention have found that some of the causes of chatter marks are caused by grinding of rolling rolls. Further, it is specified that the surface of the rolling roll has minute irregularities due to the grinding state of the rolling roll by the roll grinder before incorporating the rolling roll into the rolling machine, and the cold rolling process is performed using such a rolling roll. It was found that the vibration of the rolling mill increases depending on the combination with the rolling conditions of. The present invention has been made based on such findings.
- FIG. 1 is a diagram showing a configuration of a rolling mill according to an embodiment of the present invention.
- the rolling mill according to the embodiment of the present invention includes first to fourth (# 1 to # 4) stands in order from the entry side in the plate-passing direction.
- Other devices attached to the rolling mill for example, a rewinding machine on the entry side, a welding machine, and a looper, and a cutting machine and a winding machine on the exit side
- Each stand constituting the rolling mill shown in FIG. 1 is a four-stage rolling mill, and includes upper and lower work rolls and upper and lower backup rolls.
- reference numeral S is a steel plate
- reference numeral 1 is a work roll
- reference numeral 2 is a backup roll
- reference numeral 3a is a tension meter roll
- reference numeral 3b is a deflector roll
- reference numeral 4 is a drive device including an electric motor
- reference numeral 5 is a housing
- reference numeral 6 is a reference numeral 6.
- the vibrometer 6 a piezoelectric element type vibration sensor is suitable, but other types of vibrometers may be used.
- the vibration meter 6 is preferably installed in the housing 5. In particular, since the displacement of vibration is relatively large in the upper part of the housing 5, it is preferable to install the vibration meter 6 in the upper part of the housing 5.
- a rolling load detector consisting of a load cell 7 is provided above the backup roll on the upper side of each stand. Further, each stand is equipped with a roll speed controller, which is an electric motor for changing the roll peripheral speed of the work roll, and a roll gap controller, which changes the roll gap. Further, the tension meter roll 3a between the stands is provided with a tension meter for detecting the tension of the steel plate S. Further, a plate thickness gauge 8 for detecting the plate thickness of the steel plate S is provided on the exit side of the first stand and the fourth stand.
- the rolling mill is equipped with a roll exchange device.
- the roll exchange device is provided with a carriage capable of traveling on the rail in the axial direction of the rolling roll, and the roll exchange device takes out the used rolling roll and then charges the ground rolling roll. After use, the rolled rolls are transported to the roll shop using a crane or a transport trolley with the bearing boxes attached.
- the system for manufacturing steel products is composed of a large-scale hierarchical system for performing production control for a large number of facilities.
- the hierarchical system consists of a business computer with Level 3 at the top, a control computer (process computer) with Level 2 for each production line such as a continuous cold rolling mill, and equipment constituting each line.
- the unit is composed of layers such as a rolling control controller (PLC) which is Level 1.
- PLC rolling control controller
- the control computer is located between the upper business computer and the lower PLC, receives the manufacturing plan planned by the business computer, and gives an instruction to manufacture the steel sheet to the manufacturing line.
- the control computer collects various performance information from lower-level devices including PLC, displays them on the operation monitoring screen, performs calculations based on the theoretical model, and sends the information necessary for control to PLC. Is the main role.
- PLC gives instructions to the drives, valves, sensors, etc. that make up the manufacturing equipment at the right timing, adjusts the operation so that the devices do not interfere with each other, and physically determines the count value held by the sensor. Its main role is to operate it in association with various information.
- the system for manufacturing steel products manages a tandem mill, a rolling control controller (PLC) 11 for controlling the tandem mill, and a rolling mill including the PLC 11.
- It includes a control computer (process computer) 12 and a business computer 13 that gives manufacturing instructions to the manufacturing line.
- the control computer 12 determines the rolling operation conditions of the next steel sheet S before the welding point of the steel sheet S passes. Specifically, a path schedule is set according to information such as base metal dimensions (base material plate thickness and plate width) given by the business computer 13, product target plate thickness, etc., and the control computer 12 sets the rolling load of each stand. Determine the predicted value of the advanced rate, the roll gap, and the set value of the roll speed.
- the specification information of the rolling roll including the measured value such as the roll diameter after grinding (before charging to the stand). (Roll diameter, roll barrel length, roll number, roll material, standard classification of surface roughness, etc.) are sent to the control computer 12.
- the PLC 11 executes a process for controlling the roll speed controller of each stand and the roll gap controller of each stand based on the roll gap and roll speed set values (command values) acquired from the control computer 12. Further, the PLC 11 continuously collects rolling data such as a rolling load detected by the load cell 7 and a tension measured value by a tension meter, and outputs the rolling data to the control computer 12 at each preset cycle.
- the operating conditions of the rolling mill set or collected in the control computer 12 are sent to the rolling mill operation data output unit 14, and are input to the vibration prediction model generation unit 51, which will be described later.
- the data selected as necessary from the rolling data collected by the PLC 11 may be sent directly to the rolling mill operation data output unit 14.
- the vibration data of the rolling mill collected by the vibration meter 6 is sent to the vibration signal processing unit 15 of the rolling mill, which converts the vibration data during cold rolling by the rolling mill into vibration information.
- FIG. 2 is a diagram showing a configuration of a roll grinder according to an embodiment of the present invention.
- the roll grinder used in the present embodiment is composed of a roll grinder using a cylindrical grinding wheel.
- the rolling roll to be ground by the roll grinder is transported to the roll shop by using a crane or the like after being used in the rolling mill. After that, the rolling rolls are taken out from the bearing box, cooled to room temperature by natural cooling, and then set in the roll grinder one by one.
- the roll grinder includes a grinding head 22 that supports the grinding wheel 21, a biaxial table 23 that moves and drives the grinding head 22 in the axial direction and the approaching direction of the rolling roll 9, and a roll support device that rotates while supporting the rolling roll 9.
- Roll chuck 24, roll rotation motor 25, tailstock 26, cradle 27 are provided.
- the roll support device supports the roll chuck 24 that supports the rolling roll 9 from one end side in the axial direction, the roll rotation motor 25 that rotationally drives the rolling roll 9 at a predetermined rotation speed, and the rolling roll 9 from the other end side in the axial direction.
- the tailstock 26 and the pedestal 27 that support the rolling roll 9 at the neck portion are provided.
- the tailstock 26 has a role of aligning the axis of the rolling roll 9 with the axis of the rotation axis of the roll rotation motor 25.
- the contact portion of the tailstock 26 with the rolling roll 9 has a conical shape, and the tip of the cone is placed in the counterbore hole opened in the center of the shaft end of the rolling roll 9 or the counterbore hole of the fixing jig. It is a structure that pushes in and finely adjusts the position of the table to put out the core.
- the rotation speed of the rolling roll 9 at the time of grinding is controlled by the control controller 42 of the roll grinder.
- the biaxial table 23 has a structure that moves on the guide 28a and the guide 28b, traverses along the guide 28a arranged parallel to the axial direction of the rolling roll 9, and also traverses the grinding wheel 21 along the guide 28b.
- the movement of the biaxial table 23 along the guide 28a and the guide 28b is performed by position control using a servomotor, whereby the grinding position and the depth of cut by the grinding wheel 21 are controlled.
- grinding is performed from one end of the rolling roll 9 in the axial direction to the other end, and then grinding is performed from the other end to one end.
- the unit in which the grinding wheel 21 reciprocates once in this way is called a traverse.
- the normal grinding process is divided into a rough grinding process in which the grinding amount is set large and a finishing grinding process for finishing the surface of the rolling roll 9.
- the number of traverses for rough grinding is about 80 to 150 times
- the number of traverses for finish grinding is about 5 to 15 times.
- the grinding head 22 supports a grinding wheel 21, a grindstone rotating motor 29, a pulley 30 for transmitting grinding power, and a belt 31.
- the grinding wheel 21 may be directly driven to rotate by the grindstone rotating motor 29.
- the grindstone depth of cut refers to the amount of contact between the surface of the rolling roll 9 and the axial center portion of the grinding wheel 21 during grinding, based on the state in which the rolling roll 9 and the grinding wheel 21 are in contact with each other before each traverse.
- the grindstone rotation motor 29 Grinding conditions may be set so that the current consumption value of is the same as the current consumption value in the first traverse.
- grinding may be performed by directly using the current consumption value of the grindstone rotation motor 29 as a set value instead of the grindstone cutting amount.
- the cutting amount of the grindstone is controlled by the position control of the grinding wheel 21 by the NC device using the servo motor. Normally, the larger the cutting amount of the grindstone, the larger the grinding amount per traverse, so that the time required for roll grinding can be shortened. On the other hand, when the cutting amount of the grindstone is large, the load of the grindstone rotation motor 29 becomes excessive, which may cause a pattern-like defect on the surface of the rolling roll 9. Further, the grinding head 22 may be provided with a dressing device for the grinding wheel 21. This is a device that restores the sharpness of the grindstone by bringing diamond or the like into contact with the abrasive grains on the surface constituting the grinding wheel 21.
- the roll grinder shown in FIG. 2 is provided with a grinding operation condition setting computer (control computer) 41 of the roll grinder.
- the control computer 41 of the roll grinder acquires the dimensional information of the rolling roll 9 to be ground, the grinding amount, the target value of the surface finish roughness, etc. from the business computer 13 which is a higher-level computer, and grinds in the roll grinder.
- the conditions are set and sent to the control controller 42 of the roll grinder.
- the grinding conditions in the roll grinder include at least three setting conditions of the roll rotation speed at the time of grinding, the grinding wheel rotation speed, and the grindstone cutting amount (or the set current value of the grindstone rotation motor 29), and from rough grinding to finishing. It is set for each traverse of grinding.
- the grinding conditions in these roll grinders may be appropriately modified while the operator confirms the grinding state of the rolling roll 9.
- the ground grinding conditions in the modified roll grinder are sent to the control computer 41 of the roll grinder.
- a setting table may be provided in consideration of factors such as the diameter of the rolling roll to be ground, the surface hardness, and the surface roughness before grinding. be.
- the initial grindstone diameter is the grindstone diameter after the grinding wheel 21 is manufactured and before it is first used in roll grinding, and the current grindstone diameter is before starting grinding of the rolling roll 9 to be ground. It is the grindstone diameter measured in.
- the grindstone diameter is measured by a micrometer by selecting a plurality of outer peripheral portions of the grinding wheel 21. Further, the side surface of the grinding wheel 21 may be marked in advance with a pitch of 1 to 5 mm in the radial direction, and the grindstone diameter may be read from such a mark. The grinding wheel 21 is discarded when the initial grindstone diameter is 850 to 950 mm and the outer diameter is about 450 to 600 mm.
- the control controller 42 of the roll grinder is a roll at the time of grinding for each traverse from the start of grinding to the end of grinding with respect to the control target value of the operating conditions of the roll grindstone set by the control calculator 41 of the roll grindstone.
- Each device is controlled so that the number of rotations, the number of rotations of the grinding wheel, and the cutting amount of the grindstone (or the current value of the grindstone rotation motor) become the control target values.
- the control controller 42 of the roll grinder acquires the actual value of the motor current value for driving the grinding wheel 21 at the time of grinding. If the actual values of the roll rotation speed, the grinding wheel rotation speed, and the grindstone cutting amount during grinding can be measured, the control controller 42 of the roll grinder acquires those actual values.
- the control controller 42 of the roll grinder acquires the vibration measurement data (acceleration data).
- the data acquired in this way is sent to the control computer 41 of the roll grinder as data for analyzing the operating state of the roll grind.
- the control computer 41 of the roll grinder and the control controller 42 of the roll grinder of FIG. 2 may be configured by a single control computer.
- the peripheral speed of the grinding wheel 21 is 20 to 30 m / sec as the rotation speed of the grinding wheel, and the rotation speed of the rolling roll 9 at the time of grinding is the peripheral speed.
- the depth of cut of the grindstone per traverse is 0.5 to 1.5 m / sec, and the depth of cut is 1 to 50 ⁇ m.
- the current value of the grindstone rotation motor 29 is about 120 to 160 A as a typical value.
- the rolling roll 9 for which the finish grinding has been completed is appropriately inspected by visual inspection of the finished surface and then moved to the ground roll storage area, and when the turn comes, it is returned to the roll exchange device and rolled. It will be incorporated into the machine. At that time, all rolling rolls 9 are assigned a roll number, and the roll number is used to link the operating conditions in roll grinding and the mode incorporated in the rolling mill (the stand to be loaded or the arrangement in the stand). Can be attached.
- the specification information including the roll number of the rolling roll 9 is sent to the business computer 13 which is a higher-level computer.
- the business computer 13 is a common computer for the roll grinder and the rolling mill, and the specification information of the rolling roll 9 can be referred to from both the roll grinder and the rolling mill via the business computer 13.
- the grinding operation data recognized by the control computer 41 of the roll grinder may be sent to the rolling mill via the business computer 13.
- a dedicated server that can pass information between the roll grinder and the rolling mill may be installed. However, since there is a time lag between the timing of grinding the rolling rolls 9 and the timing of incorporating them into the rolling mill, it is necessary to secure a sufficient storage capacity.
- the vibration data of the roll grinder collected by the vibration meter 6 is sent to the vibration signal processing unit 43 of the roll grinder, and the vibration information in the roll grinder is transmitted. Is converted to.
- the vibration information in the roll grinder is also sent to the rolling mill side via the business computer 13 or a dedicated server in the same manner as described above.
- any operating condition that specifies the operating state of the roll grinder can be used.
- the grinding conditions of the roll grinder the roll rotation speed, the grindstone rotation speed, and the grindstone depth of cut set in each traverse from rough grinding to finish grinding are arbitrarily selected from all traverses. The value of may be used.
- a motor current for rotationally driving the grinding wheel 21 in an arbitrary traverse or a torque applied to the drive shaft may be used.
- a representative value for the output of the drive device in the traverse can be used, such as using the average value of the motor current and torque in the traverse.
- the grinding operation parameter may be selected from the specification information of the rolling roll 9, such as the diameter of the rolling roll 9 to be ground, the hardness of the surface, and the surface roughness.
- the count of the grinding wheel 21 the grindstone diameter (initial grindstone diameter, current grindstone diameter) and the total grinding amount (distance) after dressing by the dressing device may be used as the grinding operation parameters.
- the motor current value for driving the grinding wheel 21 in an arbitrary traverse and the cutting amount of the grinding wheel as information representing the load state on the grinding wheel for grinding the rolling roll 9 by the roll grinder (grinding wheel).
- Load parameter The motor current value that drives the grinding wheel 21 correlates with the grinding work given to the rolling roll 9 by the grinding wheel 21 during grinding, and the grindstone depth of cut correlates with the load acting on the grinding wheel 21. This is because it affects the unevenness formation of the rolling roll 9 at the time of grinding.
- the difference between the initial grindstone diameter of the grindstone 21 and the grindstone diameter (current grindstone diameter) in the state before grinding the rolling roll 9 to be ground which represents the usage history information of the grindstone 21, and the purchase of the grindstone 21
- the grinding wheel 21 is delivered in an almost circular shape by the grinding wheel manufacturer, but due to the rigidity of the grindstone and the ease of wear of the grinding wheel 21, the shape gradually deviates from the circular shape when actually used for grinding. May be. In that case, vibration that is an integral multiple of the number of rotations of the grindstone is likely to occur during roll grinding. In this case, the rolling roll 9 being ground has a periodic pattern or a profile change in the circumferential direction of the rolling roll 9 that cannot be visually confirmed. This affects the vibration behavior when the rolling roll 9 is used in the rolling mill.
- the above-mentioned grinding wheel load parameter in combination with the grinding operation parameter selected from each parameter of the grinding wheel usage history parameter. This is because slight irregularities are formed on the surface of the rolling roll 9 and the ease of formation changes depending on both the load state on the grinding wheel 21 and the deterioration / wear state of the grinding wheel 21.
- the vibration information of the roll grinder obtained by processing the signal detected by the vibration meter 6 can be included in the grinding operation parameters.
- the vibration information of the roll grinder is obtained from the processing by the vibration signal processing unit 43 of the roll grinder shown in FIG.
- the vibration meter 6 can be installed at an arbitrary position where the vibration during grinding can be measured. However, it is preferable to install it in either the grinding head 22 or the roll support device. More preferably, the position is relatively close to the grinding wheel 21 of the grinding head 22 of the roll grinder.
- the signal detected by the vibration meter 6 is vibration displacement, vibration velocity, or vibration acceleration. Therefore, the output of the vibration meter 6 may be any signal, and any index of vibration displacement, vibration velocity, and vibration acceleration may be used as the vibration information of the roll grinder. Regardless of which signal is detected, data on the vibration displacement of the grinding head 22 can be obtained.
- the vibration signal processing unit 43 of the roll grinder is realized by an arithmetic processing device such as a personal computer or a workstation, and for example, a CPU, a ROM, a RAM, or the like is a main component.
- FIG. 3 shows the processing flow in the vibration signal processing unit of the roll grinder.
- the vibration acceleration of the grinding head 22 is obtained as the signal detected by the vibration meter 6, and the vibration information of the roll grinder is obtained from the vibration speed.
- the data collected by the vibration meter 6 at this time is time-series acceleration data.
- the sampling frequency of the data detected by the vibrator 6 is 100 Hz or higher, preferably 400 Hz or higher. More preferably, it is 1000 Hz or higher.
- the acceleration data output by the vibrometer 6 for each sampling cycle is sent to the vibration acceleration data acquisition unit 43a of the roll grinder.
- the vibration acceleration data acquisition unit 43a of the roll grinder performs vibration acceleration averaging processing every predetermined data specific time (for example, 1.0 second) in order to remove the noise of the vibration meter 6, and the roll grinder It is output to the vibration speed calculation unit 43b.
- the vibration speed calculation unit 43b of the grinder calculates the vibration speed by time-integrating the vibration acceleration input at predetermined data specific time.
- the frequency analysis unit 43c of the roll grinder performs frequency analysis of the fast Fourier transform method to obtain the frequency component included in the vibration signal and its spectral value. ..
- the relationship between the frequency component and the spectral value thus obtained is used as the vibration information of the roll grinder.
- a spectral value in an arbitrary frequency band can be selected from the relationship between the frequency component and the spectral value, and the value can be used as the vibration information of the roll grinder.
- two or more frequency bands may be set as the frequency band to be selected, and the spectral values corresponding to them may be used as the vibration information of the roll grinder.
- the maximum value in the spectrum of all frequency bands may be used.
- the time-series data of the grindstone rotation frequency obtained from the rotational speed meter of the grindstone 21 is acquired.
- the dimensionless frequency is obtained by dividing the frequency band by the acquired grindstone rotation frequency, and the spectral value at the integer value (for example, 1 to 10) of the dimensionless frequency value is used as the roll grinder vibration information. May be good.
- the processing may be performed by the same method based on the vibration displacement.
- the vibration displacement can be calculated by integrating the vibration velocity over time, and by obtaining the frequency component and its spectral value by Fourier transform for the calculated vibration displacement, it is possible to obtain the vibration information of the roll grinder in the same manner as described above. It is also possible to directly use the vibration acceleration obtained by measurement. In this case, it is possible to use the result of obtaining the frequency component and its spectral value by Fourier transform on the acceleration data collected by the vibration acceleration data collecting unit 43a of the roll grinder.
- the natural frequency of the roll grinder is known in advance, the maximum value of the spectral value in the frequency band from 1/2 to 2 times the natural frequency can be used as the roll grinder vibration information.
- the roll grinder vibration information for 5 to 10 traverses before the end of the rough grinding process is calculated, and the average value thereof is used. Is preferable. Finish grinding is a step of finally adjusting the surface roughness of the rolling roll, and the slight unevenness formed on the surface of the rolling roll 9 may have already been formed at the time when the rough grinding step is almost completed. Because there are many.
- the time series data of the motor current value for driving the grinding wheel 21 at the time of roll grinding may be used instead of the time series data by the vibration meter 6.
- the roll grinder vibration information can be obtained in the same manner as described above by obtaining the frequency component and its spectral value by Fourier transform with respect to the time series data of the motor current value.
- the temporal fluctuation of the motor current value that drives the grinding wheel 21 includes information on the vibration state of the roll grinder, and is an operation that represents the vibration state of the roll grinder without installing the vibration meter 6. It is advantageous in that parameters can be obtained.
- the roll grinder vibration information acquired by the roll grinder vibration signal processing unit 43 is sent to the vibration prediction model generation unit 51 and the rolling mill vibration prediction unit 61, which will be described later.
- any rolling operation parameter for specifying the rolling state with respect to the steel plate S can be used as the rolling operation parameter of the rolling mill.
- the control computer 12 shown in FIG. 1 in order to determine the rolling conditions of the steel plate S prior to the rolling of the steel plate S, the entry-side plate thickness, the exit-side plate thickness, the entry-side tension, the exit-side tension, and the work roll are determined for each stand. The diameter, work roll rotation speed, deformation resistance, and friction coefficient are set. These can be the rolling operation parameters of the rolling mill.
- the actual values for each stand such as rolling load, tension, plate thickness, advanced rate, work roll rotation speed, roll gap, etc.
- the PLC11 is used.
- the average value for each predetermined cycle is calculated from the time-series data, and then the data is sent to the control computer 12. All of these are the rolling operation parameters of the rolling mill.
- the setting calculation values such as the rolling load, rolling torque, and advanced rate for each stand calculated in the setting calculation of the control computer 12 may be used as the rolling operation parameters of the rolling mill.
- these rolling operation parameters may be rolling operation parameters acquired for, for example, the final stand of the continuous cold rolling mill and one upstream stand thereof, as the stands where the vibration of the rolling mill tends to be large.
- vibration information of rolling mill As the vibration information during cold rolling by the rolling mill of the present embodiment, the vibration information of any stand constituting the rolling mill can be used.
- the vibration information of the stand not only the output of the vibration meter 6 installed in the housing 5 of the stand, but also the vibration meter installed in the auxiliary rolls (tension meter roll 3a and deflector roll 3b) between the stands, etc. Any information may be obtained from a detector capable of detecting the vibration state. Further, for the continuous cold rolling mill, vibration information may be collected only for the stands where chattering is likely to occur.
- the vibration information during cold rolling obtained by the vibration meter 6 installed on the upper part of the housing 5 of the stand will be described.
- the signal detected by the vibration meter 6 installed on the stand is vibration displacement, vibration velocity or vibration acceleration.
- the vibration displacement can be calculated by time-integrating the vibration speed, and the vibration speed can be calculated by time-integrating the vibration acceleration. Therefore, no matter which signal is detected, the vibration displacement data of the stand can be obtained. Can be done.
- the vibration signal processing unit 15 of the rolling mill shown in FIG. 1 is realized by an arithmetic processing device such as a personal computer or a workstation, and for example, a CPU, a ROM, a RAM, or the like is a main component.
- FIG. 4 is a diagram showing a processing example for obtaining vibration information of the rolling mill during cold rolling.
- an example of obtaining rolling mill vibration information based on the vibration speed when the vibration acceleration of the stand is obtained as the signal detected by the vibration meter 6 is shown.
- the data collected by the vibration meter 6 is time-series acceleration data.
- the sampling frequency of the data detected by the vibration meter 6 is preferably a frequency set in the range of 2,000 to 10,000 Hz. More preferably, it is 3,000 to 7,000 Hz. Select a frequency that is higher than the frequency at which chattering occurs.
- the acceleration data output by the vibration meter 6 installed on the stand for each sampling cycle is sent to the vibration acceleration data collecting unit 15a of the rolling mill provided in the vibration signal processing unit 15 of the rolling mill.
- the vibration acceleration data collecting unit 15a of the rolling mill performs vibration acceleration averaging processing at predetermined data specific time (for example, 0.2 seconds), and the vibration signal of the rolling mill. It is output to the vibration speed calculation unit 15b of the rolling mill provided in the processing unit 15.
- the vibration speed calculation unit 15b of the rolling mill calculates the vibration speed by time-integrating the vibration acceleration input at each predetermined data specific time.
- the frequency analysis unit 15c of the rolling mill provided in the vibration signal processing unit 15 of the rolling mill performs frequency analysis of the fast Fourier transform method with respect to the vibration velocity of the rolling mill thus obtained, and is included in the vibration signal. Obtain the frequency component and its spectral value.
- the relationship between the frequency component thus obtained and the spectral value is used as vibration information of the rolling mill.
- a spectral value in an arbitrary frequency band can be acquired from the relationship between the frequency component and the spectral value, and the value can be used as vibration information of the rolling mill.
- the vibration information of the rolling mill is preferably information associated with the rolling speed when the vibration signal processing unit 15 of the rolling mill acquires the data of the vibration meter 6. In that case, the spectral value in the set frequency band is acquired for each rolling speed.
- the vibration signal processing unit 15 of the rolling mill may acquire work roll peripheral speed data in addition to the signal from the vibration meter 6 installed on the stand. ..
- the vibration information of the rolling mill may be acquired only at the rolling speed at which chatter marks are likely to occur.
- the vibration information of the rolling mill may be acquired under the condition that the rolling speed is 700 to 900 m / min by setting a constant speed band. ..
- the vibration information of the rolling mill when the chatter mark occurs (with abnormal vibration) and the case where the chatter mark does not occur (abnormality). Compare with the vibration information of the rolling mill (without vibration). Then, a vibration frequency band (vibration frequency band of interest) in which the spectrum of the vibration intensity of the rolling mill when the chatter mark is generated is set, and the spectrum of the vibration intensity in the set vibration frequency band is set in the rolling mill. It can be vibration information. For example, a vibration frequency band of interest may be set, and the maximum spectral value in that frequency band may be used as vibration information of the rolling mill.
- the method for generating the vibration prediction model of the rolling mill of the present embodiment is the grinding operation parameter of the roll grinder in the rolling process in which the steel plate S is cold-rolled by the rolling mill using the rolling roll 9 ground by the roll grinder.
- the actual data selected from and the actual data selected from the rolling operation parameters of the rolling mill were used as the input actual data, and the vibration information of the rolling mill during cold rolling using the input actual data was used as the output actual data. It includes a learning step of acquiring a plurality of training data and generating a rolling mill vibration prediction model by machine learning using the acquired multiple training data.
- Actual data is sent from the grinding operation data output unit 44 to the vibration prediction model generation unit 51 shown in FIG. 6 as the grinding operation parameters of the roll grinder, and the roll grinder vibration information is sent as needed. Further, as for the rolling operation parameters of the rolling mill, actual data is sent by the rolling mill operation data output unit 14 through the control computer 12. Further, the specification information of the rolling roll 9 incorporated in the rolling mill is sent from the business computer 13 to the vibration prediction model generation unit 51 via the control computer 12 with reference to the roll number of the rolling roll 9. On the other hand, as for the vibration information of the rolling mill when rolling is performed under those operating conditions, the vibration information of the rolling mill processed by the vibration signal processing unit 15 of the rolling mill is sent to the vibration prediction model generation unit 51. ..
- the vibration prediction model generation unit 51 the actual data of the grinding operation parameters selected from the actual data of the roll grinder and the actual data of the rolling operation parameters selected from the actual data of the operating conditions of the rolling mill. , And the vibration information of the rolling mill is stored in the database 51a. At that time, since the roll number of the rolling roll 9 incorporated in the rolling mill is recognized by the rolling mill control computer 12, the data is linked based on the roll number, and the data set is obtained. Is constructed and stored in the database 51a.
- the vibration prediction model generation unit 51 collects a plurality of collected input data and output data data sets and stores them in the database 51a.
- the number of data in the database 51a it is preferable that at least 100 or more, preferably 500 or more, and more preferably 1000 or more data are accumulated.
- the machine learning unit 51b uses the accumulated data set to at least select from the actual data selected from the grinding operation parameters of the roll grinder and the rolling operation parameters of the steel plate S in the rolling machine.
- the selected actual data is used as the input actual data
- the vibration information of the rolling mill using the input actual data is used as the output actual data to generate the rolling mill vibration prediction model M by machine learning.
- a known learning method may be applied.
- a known machine learning method such as a neural network (deep learning, convolutional neural network, etc.) may be used.
- Other methods include decision tree learning, random forest, support vector regression, Gaussian process, and the like.
- an ensemble model in which a plurality of models are combined may be used.
- the vibration prediction model M of the rolling mill may be appropriately updated using the latest learning data.
- the grinding operation parameter of the roll grinder which is the input to the vibration prediction model M of the rolling mill of the present embodiment
- the grinding operation parameter for either the upper and lower work rolls or the upper and lower backup rolls may be selected. good.
- the vibration prediction model generation unit does not determine the parameter to be selected in advance. Actual data may be accumulated in the database 51a of 51 and appropriately selected when the machine learning unit 51b generates the vibration prediction model M.
- the input data of the vibration prediction model M of the present embodiment includes both the actual data selected from the grinding operation parameters of the roll grinder and the actual data selected from the rolling operation parameters of the rolling mill.
- the inventors of the present invention have one of the causes of chatter marks due to the vibration of the rolling mill during cold rolling of the steel sheet S due to the slight unevenness of the surface generated by the grinding of the rolling roll 9. I have obtained the knowledge. In that case, the chatter mark does not occur only by the operating conditions of the rolling mill. On the other hand, it has been found that even if the surface of the rolling roll 9 has slight irregularities, the periodic fluctuation of the rolling mill does not necessarily occur, but it is caused by the combination with a specific rolling operation condition. Therefore, in the vibration prediction model M of the present embodiment, both the grinding operation parameters of the roll grinder and the rolling operation parameters of the rolling mill are input.
- the vibration of the rolling mill is predicted using the vibration prediction model M of the rolling mill generated as described above.
- the timing of vibration prediction is set by the control computer before the tip of the steel plate (steel plate joined on the entrance side of the continuous cold rolling mill) S to be predicted is loaded into the first stand of the rolling mill. It is preferable after the setting calculation of the steel sheet S to be rolled by 12 is completed. This is because the rolling operation parameters such as the rolling load calculated by the control computer 12 can be specified as the input value of the vibration prediction model M of the rolling mill. Further, before the rolling of the steel sheet S is started, it is possible to prevent the occurrence of chattering by appropriately modifying the pass schedule of the target material.
- actual data is sent from the grinding operation data output unit 44 as a grinding operation parameter of the roll grinder to the rolling mill vibration prediction unit 61, and the roll grinder is used as necessary. Vibration information is sent. Further, as the rolling operation parameter of the rolling mill, the set value of the rolling mill operation parameter is sent from the rolling mill operation data output unit 14. Using these as input data, the rolling mill vibration prediction unit 61 obtains a predicted value of the rolling mill vibration information in cold rolling of the steel plate S by using the rolling mill vibration prediction model M (first step).
- the upper limit value of the rolling mill vibration is preset in the rolling mill control computer 12 as the vibration level of the rolling mill in which the chatter mark does not occur, and the upper limit value is sent to the abnormal vibration determination unit 61a.
- the rolling mill vibration upper limit value is set based on past data or the like in a frequency band where chatter marks are likely to occur. Specifically, a spectral value at which chatter mark does not occur or has a low probability of occurring can be calculated from past data and set as an upper limit value (roller vibration upper limit value).
- the abnormal vibration determination unit 61a compares the vibration prediction result predicted by using the rolling mill vibration prediction model M with respect to the rolling mill vibration upper limit value preset as described above. If the vibration prediction result is equal to or less than the rolling mill vibration upper limit value, the abnormal vibration determination unit 61a sets the operating conditions for cold rolling of the steel sheet with the initial settings, and determines the instruction of the operating conditions to the PLC 11. .. On the other hand, when the vibration prediction result exceeds the rolling mill vibration upper limit value, the abnormal vibration determination unit 61a determines that abnormal vibration occurs in the cold rolling of the steel plate S (second step).
- the abnormal vibration determination unit 61a is at a stage before the start of cold rolling of the steel plate S or after the start of cold rolling of the steel plate S and before being accelerated to the maximum speed set for the steel plate S.
- Reset the operating conditions for cold rolling (resetting step).
- the rolling path schedule can be reset.
- the control target value of the tension between stands may be reset.
- the occurrence of chattering is suppressed by resetting the preset maximum speed for the steel sheet S and determining the rolling operation conditions in the speed range where chattering does not occur (lower the set value of the maximum speed). Chattering can be avoided by known means that can be done. As a result, the steel sheet S having a good yield can be manufactured, and the productivity of the rolling mill can be improved.
- Example 1 a vibration prediction model of the rolling mill in the 4-stand continuous cold rolling mill shown in FIG. 1 was generated.
- the target rolling roll has a roll barrel length of 1750 mm, a total length of 2300 mm, and a roll diameter of 1451 mm.
- an alumina-based grindstone was used as the grinding grindstone.
- the diameter of the grindstone was ⁇ 910 mm at the time of delivery, 650 mm at the time of grinding, the rotation speed of the grindstone was 620 rpm, and the set current value of the motor for rotating the grindstone was set to 120 A at the time of rough grinding and 50 A at the time of finish grinding.
- the operating parameters of the roll grinder the initial grindstone diameter, the pre-use grindstone diameter, the grindstone rotary motor load current, and the roll rotary motor load current were used.
- an accelerometer was installed in the roll grinder as the vibrometer 6 shown in FIG. 2, and vibration information of the roll grinder was acquired. Accelerometers collect acceleration data at a sampling frequency of 1000 Hz, and in order to remove accelerometer noise, vibration acceleration is averaged every predetermined data specific time (1.0 seconds), and the roll grinder uses a roll grinder. It was output to the vibration speed calculation unit. The vibration speed calculation unit of the roll grinder calculated the vibration speed by time-integrating the vibration acceleration input at each data specific time. Further, in the frequency analysis unit of the roll grinder, the frequency analysis of the fast Fourier transform method was performed, and the frequency component included in the vibration signal and its spectral value were obtained.
- the natural frequency of the roll grinder is 42 Hz
- a component having a frequency of 22 to 62 Hz (natural frequency ⁇ 20 Hz) close to the natural frequency is used.
- the vibration in the frequency band (however, the bandwidth of ⁇ 2 Hz was set), which is an integral multiple of the rotation speed of the grindstone of 10.3 Hz.
- the spectral values (four circled in the example shown in FIG. 9) in the frequency band in the frequency range of 22 to 62 Hz, which is an integral multiple of the grindstone rotation speed, are used as the vibration information of the roll grinder. ..
- the natural frequency of the roll grinder was identified based on the characteristics of the impulse response to the external force of the hammer.
- the average value of 10 traverses up to the end of rough grinding of the backup roll was used as the four spectral values in the frequency band.
- the rolling speed, rolling rate, and advanced rate are used as rolling mill operation data when the lower backup roll of the third stand ground in this way is incorporated into the continuous cold rolling mill and cold rolling of the steel sheet is performed. , Deformation resistance of steel sheet, and rolling performance data of rolling load were acquired, and these were used as rolling operation parameters.
- the vibration information of the rolling mill was based on the acceleration data acquired by the vibration meter installed in the upper part of the housing of the third stand in the rolling mill shown in FIG.
- the sampling frequency of the vibration meter was set to 2000 Hz, and the vibration acceleration was averaged and time-integrated every predetermined data specific time (1.0 second) to acquire time-series data of the vibration velocity.
- the frequency analysis of the fast Fourier transform method was performed on the vibration velocity of the rolling mill thus obtained, and the frequency components included in the vibration signal and their spectral values were obtained as actual data.
- the actual data acquired in this way was accumulated in the database 51a shown in FIG. Then, a vibration prediction model of the rolling mill by machine learning was generated using 500 data from the accumulated database 51a. Specifically, the grinding operation parameters of the roll grinder of the backup roll, the vibration information of the roll grinder, and the rolling operation parameters when the steel plate is rolled by using the backup roll as the backup roll under the third stand are input.
- the maximum value of the spectral value in the frequency band 350 to 900 Hz which is the vibration information of the rolling mill, was used as the output actual data.
- a neural network was used for the machine learning method, the middle layer was set to 3 layers, and the number of nodes was set to 5 each.
- the activation function used was the sigmoid function.
- Example 2 a vibration prediction model of a rolling mill in a 5-stand continuous cold rolling mill was generated.
- the configuration of the rolling mill is the same as that of the 4-stand continuous cold rolling mill shown in FIG.
- the rolling mill of this embodiment is a continuous cold rolling mill for producing a metal strip having a larger plate width than the rolling mill of the first embodiment, and the body length of the work roll is the same as that of the first embodiment. Longer than that.
- the actual values of the grinding operation parameters when they are ground by the roll grinder, and when they are incorporated into the above rolling mill and rolled were accumulated in the database 51a of the vibration prediction model generation unit 51.
- the target backup roll had a roll barrel length of 1981 mm, a total length of 2300 mm, and a diameter of 1260 to 1480 mm.
- the grinding wheel used in the roll grinder for grinding such a backup roll is a white alumina-based grindstone, and a grindstone having a grindstone diameter (initial grindstone diameter) of ⁇ 850 to 910 mm at the time of purchasing the grindstone was selected.
- the diameter of the pre-use grindstone measured before grinding the backup roll was in the range of ⁇ 490 to 910 mm.
- the grindstone rotation speed during grinding is 360 rpm to 900 rpm
- the set current value of the motor that rotates the grindstone is set in the range of 100 to 140 A in the rough grinding process and in the range of 50 to 80 A in the finish grinding process.
- the cutting amount of the grindstone was set so that the current value would be in such a range.
- an accelerometer was installed as a vibrometer on the grinding head of the roll grinder to acquire grinding information of the roll grinder when grinding the backup roll. As the grinding information of the roll grinder, the information acquired from the accelerometer in the rough grinding process for 10 traverses before the start of the grinding path of the finish grinding process when shifting from the rough grinding process to the finish grinding process was used. ..
- the accelerometer installed in the roll grinder acquires acceleration data at a sampling frequency of 1000 Hz and performs vibration acceleration averaging processing at predetermined data specific time (1.0 seconds) in order to remove noise in the acceleration data. Then, it was output to the vibration speed calculation unit 43b of the roll grinder.
- the vibration speed calculation unit 43b of the roll grinder calculated the vibration speed by time-integrating the vibration acceleration input at each data specific time.
- the frequency analysis unit 43c of the roll grinder performed a high-speed Fourier transform frequency analysis to obtain a frequency component included in the vibration signal and its spectral value.
- the vibration of the frequency band (however, the bandwidth of ⁇ 2 Hz is set) that is three, four, five, and six times the frequency of the grindstone rotation speed.
- the largest spectral value was selected. Further, the average value of the spectral values selected so during the final 10 traverses of the rough grinding process was used as the vibration information of the roll grinder. Further, in this embodiment, in addition to the vibration information of the roll grinder as the grinding operation parameters of the roll grinder, the initial grindstone diameter and the pre-use grindstone diameter for the grindstone, the grindstone rotation speed and the grindstone depth of cut as the grinding conditions. , Grindstone rotary motor load current was selected. Further, as the grinding operation parameters of the roll grinder, the diameter of the backup roll, the roll rotation speed at the time of grinding, and the motor load current for the roll rotation were selected, and these actual values were accumulated in the database 51a.
- the backup roll ground by the roll grinder is used as the upper backup roll and the lower backup roll of the fourth stand of the continuous cold rolling machine, and the actual values of the rolling operation parameters at that time are acquired.
- the rolling operation parameters of the rolling mill collected in the database 51a include the entry-side plate thickness and exit-side plate thickness of the 4th stand of the steel plate to be rolled, the front tension, the back tension, the advanced ratio, the deformation resistance, the rolling load, and the vertical work roll. The average diameter was selected.
- the rolling speed (workroll peripheral speed of the final stand) when acquiring these actual data was added, and all nine types of rolling actual data were acquired. These actual data were used as actual values of rolling operation parameters of the rolling mill by averaging the sampling data every second.
- the measured values of the vibration information of the rolling mill were acquired.
- the vibration information of the rolling mill was calculated from the acceleration data acquired by the vibration meter installed in the upper part of the housing of the 4th stand. Accelerometer data was acquired from the acceleration sensor installed in the rolling mill under the condition of a sampling frequency of 2000 Hz. The acquired acceleration data was obtained as time-series data of vibration velocity by performing vibration acceleration averaging processing and time integration at predetermined data specific time (1.0 seconds). The frequency analysis of the fast Fourier transform method was performed on the vibration velocity of the rolling mill thus obtained, and the frequency components included in the vibration signal and their spectral values were obtained as actual data.
- the steel sheets used for rolling include mild steels including ultra-low carbon steel to high-strength steel sheets with a tensile strength of 1.5 GPa, and the plate thickness is 2 to 6 mm on the input side of the rolling mill and 0.6 mm on the exit side of the final stand. The thickness was 2.8 mm, the plate width was 750 mm to 1880 mm, and the rolling reduction in the fourth stand was 5% to 40%.
- the vibration prediction model of the rolling mill was generated.
- the following four types of vibration prediction models for the generated rolling mill were used.
- Example 1 of the present invention in which input data is selected from both the grinding operation parameters of the roll grinder and the rolling operation parameters of the rolling mill.
- There are four grinding operation parameters for the roll grinder the initial grindstone diameter when grinding the upper backup roll, the grindstone diameter before use, the grindstone rotation speed, and the grindstone rotation motor load current, and the initial grindstone diameter when grinding the lower backup roll.
- the rolling reduction, rolling load, and rolling speed were selected from the rolling operation parameters of the rolling mill.
- Example 2 of the present invention in which input data is selected from both the grinding operation parameters of the roll grinder and the rolling operation parameters of the rolling mill.
- the number of grindstone rotations and the load current of the grindstone rotation motor were selected.
- the rolling operation parameters of the rolling mill were selected from three factors: rolling reduction, deformation resistance, and rolling speed.
- the vibration prediction model of the rolling mill was generated for each of the input data of Examples 1 and 2 and Comparative Examples 1 and 2 of the present invention by machine learning using the output data as the vibration information of the rolling mill.
- a neural network was used for the machine learning method, the middle layer was set to 3 layers, and the number of nodes was set to 5 each.
- the ReLU function was used as the activation function.
- the vibration of the rolling mill was predicted with respect to the actual data of rolling 2500 coils as test data.
- the vibration of the rolling mill was determined by the output of the vibration meter installed in the housing of the 4th stand.
- the abnormal vibration of the rolling mill was determined to be abnormal vibration when the vibration of the rolling mill was larger than the maximum spectral value of 0.03 mm / sec in the frequency band of 350 to 900 Hz as a threshold.
- the vibration information of the rolling mill which is the output of the vibration prediction model of the rolling mill, exceeds 0.03 mm / sec, it is predicted to be abnormal vibration.
- the 2500 coils which are the test data, were predicted to have abnormal vibration by the vibration prediction model of the rolling mill, the number of coils determined to have abnormal vibration by the vibration meter of the rolling mill was set to I1.
- the number of coils determined to have no abnormal vibration by the vibration meter of the rolling mill was defined as I2.
- the ratio of the sum of I1 and I2 to the total number of coils of 2500 coils is called the matching rate.
- the concordance rate of Comparative Example 1 was 38%. It is considered that this is because the rolling mill vibration, which is determined only by the rolling conditions, could be calculated accurately, but the prediction accuracy is low for the rolling mill vibration, which is the root cause of the backup roll.
- the concordance rate of Comparative Example 2 was 48%. While this reflects the rolling mill vibration caused by the unevenness of the backup roll to some extent, the rolling mill vibration caused by the rolling conditions and the unevenness of the backup roll do not cause abnormal vibration depending on the rolling conditions. It is probable that it was not possible to make a sufficient prediction.
- the concordance rate of Example 1 of the present invention was 85%.
- Example 2 of the present invention was 93%. It is considered that this is because the prediction accuracy of the abnormal vibration of the rolling mill was improved by adding the vibration information of the roll grinder to the input.
- the present invention it is possible to provide a method for predicting vibration of a rolling mill that can predict the vibration of the rolling mill before rolling the metal strip. Further, according to the present invention, it is possible to provide a method for determining abnormal vibration of a rolling mill that can predict abnormal vibration of the rolling mill before rolling the metal strip. Further, according to the present invention, it is possible to provide a method for rolling a metal strip, which can suppress the generation of chatter marks and improve the manufacturing yield of the metal strip. Further, according to the present invention, it is possible to provide a method for generating a vibration prediction model of a rolling mill capable of generating a vibration prediction model of a rolling mill that predicts the vibration of the rolling mill before rolling a metal strip.
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
Description
本実施形態において用いる圧延機は、連続式冷間圧延機であり、主として4~6スタンドのタンデムミルを対象とする。但し、本発明は、単スタンドのリバース式圧延機にも適用でき、タンデムミルのスタンド数もこれに限定されない。図1は、本発明の一実施形態である圧延機の構成を示す図である。図1に示すように、本発明の一実施形態である圧延機は、通板方向の入側から順に第1~第4(#1~#4)スタンドを備えている。なお、圧延機に附帯する他の装置(例えば入側の巻戻機、溶接機、及びルーパ、並びに出側の切断機及び巻取機等の装置)については図示を省略している。図1に示す圧延機を構成する各スタンドは4段式圧延機であり、上下のワークロール及び上下のバックアップロールを備えている。
図2は、本発明の一実施形態であるロール研削機の構成を示す図である。図2に示すように、本実施形態において使用するロール研削機は、円筒型研削砥石を用いたロール研削機により構成されている。ロール研削機の研削対象となる圧延ロールは、圧延機にて使用された後にクレーン等を用いてロールショップに運搬される。その後、圧延ロールは、軸受箱から抜き出し、自然放冷により常温まで冷却された後、1本ずつロール研削機にセットされる。
本実施形態に用いる研削操業パラメータとしては、上記のロール研削機の操業状態を特定する任意の操業条件を用いることができる。例えば、ロール研削機の研削条件として、粗研削から仕上研削の各トラバースで設定される研削時のロール回転数、研削砥石回転数、及び砥石切込み量について、全トラバースから任意に選択したトラバースにおけるこれらの値を用いてもよい。また、任意のトラバースにおける研削砥石21を回転駆動するモータ電流や、その駆動軸に負荷されるトルクを用いてもよい。この場合には、トラバース中のモータ電流やトルクの平均値を用いる等、そのトラバースにおける駆動装置の出力についての代表値を用いることができる。さらに、研削対象となる圧延ロール9の直径、表面の硬度、表面粗さ等、圧延ロール9の諸元情報の中から研削操業パラメータを選択してもよい。一方、研削砥石21の操業条件として、研削砥石21の番手、砥石径(初期砥石径、現砥石径)やドレス装置によるドレス後の総研削量(距離)を研削操業パラメータとして用いてもよい。
ロール研削機が振動計6を備える場合、振動計6で検出された信号を処理することにより得られるロール研削機の振動情報を研削操業パラメータに含めることができる。ロール研削機の振動情報は、図2に示すロール研削機の振動信号処理部43による処理から得られる。ロール研削機が振動計6を備える場合、振動計6は、研削時の振動を測定可能な任意の位置に設置することができる。但し、研削ヘッド22及びロール支持装置のいずれかに設置するのが好ましい。より好ましくは、ロール研削機の研削ヘッド22の研削砥石21に比較的近い位置である。
本実施形態では、圧延機の圧延操業パラメータとして、鋼板Sに対する圧延状態を特定するための任意の圧延操業パラメータを用いることができる。図1に示す制御用計算機12においては、鋼板Sの圧延に先立って鋼板Sの圧延条件を決定するために、スタンド毎に入側板厚、出側板厚、入側張力、出側張力、ワークロール径、ワークロール回転数、変形抵抗、及び摩擦係数が設定される。これらは、圧延機の圧延操業パラメータとすることができる。
本実施形態の圧延機による冷間圧延時の振動情報は、圧延機を構成する任意のスタンドの振動情報を用いることができる。スタンドの振動情報として、スタンドのハウジング5に設置した振動計6の出力だけでなく、スタンド間の補助ロール(テンションメータロール3aやデフレクターロール3b)に設置した振動計等、圧延中の圧延機の振動状態を検出できる検出器によって得られる情報であればよい。また、連続式冷間圧延機については、特にチャタリングが発生しやすいスタンドに限定して振動情報を採取してもよい。ここでは、スタンドのハウジング5上部に設置した振動計6によって得られる冷間圧延時の振動情報について説明する。
本実施形態の圧延機の振動予測モデルの生成方法は、ロール研削機によって研削された圧延ロール9を用いて圧延機により鋼板Sの冷間圧延を行う圧延工程において、ロール研削機の研削操業パラメータから選択した実績データと、圧延機の圧延操業パラメータから選択した実績データとを、入力実績データとし、その入力実績データを用いた冷間圧延時における圧延機の振動情報を出力実績データとした、複数の学習用データを取得し、取得した複数の学習用データを用いた機械学習によって圧延機の振動予測モデルを生成する学習ステップを含む。
本実施形態の振動予測方法では、以上のようにして生成した圧延機の振動予測モデルMを用いた圧延機の振動予測を行う。振動予測を行うタイミングは、予測対象とする鋼板(連続式冷間圧延機の入側で接合された鋼板)Sの先端部が圧延機の第1スタンドに装入される前として、制御用計算機12による圧延対象の鋼板Sの設定計算が完了した後が好ましい。制御用計算機12によって計算される圧延荷重等の圧延操業パラメータを圧延機の振動予測モデルMの入力値として特定できるからである。また、鋼板Sの圧延を開始する前であれば、対象材のパススケジュールを適宜修正する等、チャタリングの発生を未然に防止することができるからである。
本実施例では、図1に示す4スタンドの連続式冷間圧延機における圧延機の振動予測モデルを生成した。本実施例では、第3スタンドの下バックアップロールに着目し、当該バックアップロールのロール研削機における研削操業パラメータの実績データを採取した。対象とした圧延ロールは、ロールバレル長1750mm、全長2300mm、ロール径1451mmである。ロール研削機では、研削砥石としてアルミナ系砥石を使用した。砥石径は納入時φ910mm、研削時は650mmで、砥石回転数は620rpmとし、砥石を回転するモータの設定電流値は、粗研削時120A、仕上研削時50Aとなるよう砥石切込み量を設定した。このとき、ロール研削機の操業パラメータとしては、初期砥石径、使用前砥石径、砥石回転モータ負荷電流、及びロール回転モータ負荷電流を用いた。
本実施例では、5スタンドの連続式冷間圧延機における圧延機の振動予測モデルを生成した。圧延機の構成は、図1に示す4スタンドの連続式冷間圧延機と同様である。但し、本実施例の圧延機は、上記実施例1の圧延機よりも板幅が大きな金属帯を製造するための連続式冷間圧延機であり、ワークロールの胴長が上記実施例1のそれよりも長い。本実施例では、5スタンドの連続式冷間圧延機における第4スタンドのバックアップロールに着目した。すなわち、本実施例では、第4スタンドの上側及び下側のバックアップロールについて、それらをロール研削機により研削した際の研削操業パラメータの実績値、それらを上記圧延機に組み込んで圧延を行った際の圧延操業パラメータの実績値、及び第4スタンドのハウジング上部に設置した振動計によって取得された圧延機の振動情報の実績値を振動予測モデル生成部51のデータベース51aに蓄積した。
ロール研削機の研削操業パラメータとして、上バックアップロールの研削時における初期砥石径、使用前砥石径、砥石回転数、砥石回転モータ負荷電流の4つと、下バックアップロールの研削時における初期砥石径、使用前砥石径、砥石回転数、砥石回転モータ負荷電流の4つを選択した。また、圧延機の圧延操業パラメータからは圧下率、圧延荷重、圧延速度の3つを選択した。
ロール研削機の研削操業パラメータとして、上バックアップロールの研削時におけるロール研削機の振動情報、砥石回転数、砥石回転モータ負荷電流の3つと、下バックアップロールの研削時におけるロール研削機の振動情報、砥石回転数、砥石回転モータ負荷電流の3つを選択した。また、圧延機の圧延操業パラメータから、圧下率、変形抵抗、圧延速度の3つを選択した。
圧延機の圧延操業パラメータとして、第4スタンドの入側板厚と出側板厚、前方張力、後方張力、先進率、変形抵抗、圧延荷重、上下ワークロールの平均径、及び圧延速度の9つを選択した。
ロール研削機の研削操業パラメータとして、上バックアップロールの研削時におけるロール研削機の振動情報、初期砥石径、使用前砥石径、砥石回転数、砥石切込み量、砥石回転モータ負荷電流、上バックアップロールの直径、研削時のロール回転数、ロール回転用のモータ負荷電流の9個と、下バックアップロールの研削時におけるロール研削機の振動情報、初期砥石径、使用前砥石径、砥石回転数、砥石切込み量、砥石回転モータ負荷電流、下バックアップロールの直径、研削時のロール回転数、ロール回転用のモータ負荷電流の9個を選択した。
2 バックアップロール
3a テンションメータロール
3b デフレクターロール
4 駆動装置
5 ハウジング
6 振動計
7 ロードセル
8 板厚計
9 圧延ロール
11 圧延制御コントローラ(PLC)
12 制御用計算機(プロセスコンピュータ)
13 ビジネスコンピュータ
14 圧延機操業データ出力部
15 圧延機の振動信号処理部
15a 圧延機の振動加速度データ収集部
15b 圧延機の振動速度計算部
15c 圧延機の周波数解析部
21 研削砥石
22 研削ヘッド
23 二軸テーブル
24 ロールチャック
25 ロール回転モータ
26 芯押し台
27 受け台
28a,28b ガイド
29 砥石回転用モータ
30 プーリー
31 ベルト
41 ロール計算機の研削操業条件設定計算機(制御用計算機)
42 ロール研削機の制御用コントローラ
43 ロール研削機の振動信号処理部
43a ロール研削機の振動加速データ収集部
43b ロール研削機の振動速度計算部
43c ロール計算機の周波数解析部
44 研削操業データ出力部
51 振動予測モデル生成部
51a データベース
51b 機械学習部
61 圧延機振動予測部
61a 異常振動判定部
M 圧延機の振動予測モデル
S 鋼板
Claims (7)
- ロール研削機によって研削された圧延ロールを用いて圧延機により金属帯を圧延する圧延工程における前記圧延機の振動を予測する圧延機の振動予測方法であって、
入力データとして、前記ロール研削機の研削操業パラメータから選択した1又は2以上のパラメータと、前記圧延機の圧延操業パラメータから選択した1又は2以上のパラメータと、を含み、圧延工程における前記圧延機の振動情報を出力データとした、機械学習により学習された圧延機の振動予測モデルを用いて、前記圧延機の振動を予測するステップを含む、圧延機の振動予測方法。 - 前記研削操業パラメータは、前記圧延ロールを前記ロール研削機により研削する際に取得されるロール研削機の振動情報を含む、請求項1に記載の圧延機の振動予測方法。
- 前記研削操業パラメータは、前記圧延ロールを前記ロール研削機により研削するときの研削砥石への負荷情報に関する研削砥石負荷パラメータと前記研削砥石の使用履歴情報に関する研削砥石使用履歴パラメータとを含む、請求項1又は2に記載の圧延機の振動予測方法。
- 請求項1~3のうち、いずれか1項に記載の圧延機の振動予測方法を用いて、前記ロール研削機により研削した圧延ロールを前記圧延機に組み込んだ後であって、金属帯の圧延を開始する前に、前記ロール研削機の研削操業パラメータの実績値と、前記圧延機の圧延操業パラメータの設定値を用いて、前記金属帯を圧延する際の圧延機の振動を予測する第1ステップと、
前記第1ステップによる振動の予測結果と予め設定された圧延機の振動の上限値との比較に基づいて、前記圧延機の異常振動の発生の有無を判定する第2ステップと、
を含む、圧延機の異常振動判定方法。 - 請求項4に記載の圧延機の異常振動判定方法を用いて圧延機の異常振動が発生すると判定された場合に、前記圧延機の圧延操業条件を再設定するステップを含む、金属帯の圧延方法。
- ロール研削機によって研削された圧延ロールを用いて圧延機により金属帯を圧延する圧延工程における前記圧延機の振動を予測する圧延機の振動予測モデルを生成する圧延機の振動予測モデルの生成方法であって、
前記ロール研削機の研削操業パラメータから選択した実績データと、前記圧延機の圧延操業パラメータから選択した実績データとを、入力実績データとし、その入力実績データを用いた金属帯の圧延における前記圧延機の振動情報を出力実績データとした、複数の学習用データを取得し、取得した複数の学習用データを用いた機械学習によって前記圧延機の振動予測モデルを生成する学習ステップを含む、圧延機の振動予測モデルの生成方法。 - 前記機械学習として、ニューラルネットワーク、決定木学習、ランダムフォレスト、及びサポートベクター回帰から選択した機械学習を用いる、請求項6に記載した圧延機の振動予測モデルの生成方法。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202180053629.0A CN116157214A (zh) | 2020-09-04 | 2021-08-04 | 轧机的振动预测方法、轧机的异常振动判定方法、金属带的轧制方法及轧机的振动预测模型的生成方法 |
JP2021559210A JP7131714B2 (ja) | 2020-09-04 | 2021-08-04 | 圧延機の振動予測方法、圧延機の異常振動判定方法、金属帯の圧延方法、及び圧延機の振動予測モデルの生成方法 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2020-148663 | 2020-09-04 | ||
JP2020148663 | 2020-09-04 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022049975A1 true WO2022049975A1 (ja) | 2022-03-10 |
Family
ID=80492024
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2021/028936 WO2022049975A1 (ja) | 2020-09-04 | 2021-08-04 | 圧延機の振動予測方法、圧延機の異常振動判定方法、金属帯の圧延方法、及び圧延機の振動予測モデルの生成方法 |
Country Status (3)
Country | Link |
---|---|
JP (1) | JP7131714B2 (ja) |
CN (1) | CN116157214A (ja) |
WO (1) | WO2022049975A1 (ja) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP7332077B1 (ja) * | 2022-05-27 | 2023-08-23 | Jfeスチール株式会社 | ロール研削機の異常振動予測方法、圧延ロールの研削方法、金属帯の圧延方法、ロール研削機の異常振動予測装置及びロール研削設備 |
WO2023228483A1 (ja) * | 2022-05-27 | 2023-11-30 | Jfeスチール株式会社 | ロール研削機の異常振動予測方法、圧延ロールの研削方法、金属帯の圧延方法、ロール研削機の異常振動予測装置及びロール研削設備 |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103886373A (zh) * | 2014-04-18 | 2014-06-25 | 天津理工大学 | 基于bp神经网络的高速冷轧机第三倍频程颤振预测方法 |
-
2021
- 2021-08-04 JP JP2021559210A patent/JP7131714B2/ja active Active
- 2021-08-04 CN CN202180053629.0A patent/CN116157214A/zh active Pending
- 2021-08-04 WO PCT/JP2021/028936 patent/WO2022049975A1/ja active Application Filing
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103886373A (zh) * | 2014-04-18 | 2014-06-25 | 天津理工大学 | 基于bp神经网络的高速冷轧机第三倍频程颤振预测方法 |
Non-Patent Citations (2)
Title |
---|
CASPARIC, JONE J: "Vibration analysis identifies the causes of mill chatter", IRON AND STEEL ENGINEER, vol. 68, no. 2, 28 February 1991 (1991-02-28), pages 27 - 29, XP000176976 * |
NESSLER, GERALD L. ET AL.: "Identification of chatter sources in cold rolling mills", IRON AND STEEL ENGINEER, vol. 70, no. 1, 31 January 1993 (1993-01-31), pages 40 - 45, XP000336824 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP7332077B1 (ja) * | 2022-05-27 | 2023-08-23 | Jfeスチール株式会社 | ロール研削機の異常振動予測方法、圧延ロールの研削方法、金属帯の圧延方法、ロール研削機の異常振動予測装置及びロール研削設備 |
WO2023228483A1 (ja) * | 2022-05-27 | 2023-11-30 | Jfeスチール株式会社 | ロール研削機の異常振動予測方法、圧延ロールの研削方法、金属帯の圧延方法、ロール研削機の異常振動予測装置及びロール研削設備 |
Also Published As
Publication number | Publication date |
---|---|
CN116157214A (zh) | 2023-05-23 |
JPWO2022049975A1 (ja) | 2022-03-10 |
JP7131714B2 (ja) | 2022-09-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2022049975A1 (ja) | 圧延機の振動予測方法、圧延機の異常振動判定方法、金属帯の圧延方法、及び圧延機の振動予測モデルの生成方法 | |
US6306007B1 (en) | Rolling mill equipped with on-line roll grinding system and grinding wheel | |
CN109078989B (zh) | 一种六辊冷轧机的极限轧制速度预测方法 | |
JP2015036154A (ja) | 冷間タンデム圧延機における走間板厚変更方法 | |
Ubici et al. | Identification and countermeasures to resolve hot strip mill chatter | |
WO2022049976A1 (ja) | 圧延ロールの研削合否判定装置、圧延ロールの研削合否判定方法、及び金属帯の圧延方法 | |
JP6841264B2 (ja) | 冷間圧延における異常振動検出方法 | |
JP6879057B2 (ja) | 監視システム | |
WO2022209295A1 (ja) | 圧延機の異常振動検出方法、異常検出装置、圧延方法および金属帯の製造方法 | |
WO2023228483A1 (ja) | ロール研削機の異常振動予測方法、圧延ロールの研削方法、金属帯の圧延方法、ロール研削機の異常振動予測装置及びロール研削設備 | |
CN101939118A (zh) | 钢板带轧制方法及钢板制造方法 | |
JP7332077B1 (ja) | ロール研削機の異常振動予測方法、圧延ロールの研削方法、金属帯の圧延方法、ロール研削機の異常振動予測装置及びロール研削設備 | |
JPH07195255A (ja) | 圧延ロールの自動研削装置 | |
JP7243944B1 (ja) | 圧延ロールの適合判定方法、金属帯の圧延方法及び冷延鋼板の製造方法 | |
WO2023079850A1 (ja) | 圧延ロールの適合判定方法、金属帯の圧延方法及び冷延鋼板の製造方法 | |
CN115008261A (zh) | 一种轧辊拖肩的修复方法 | |
JP3276002B2 (ja) | オンラインロールグラインダによる圧延ロール表面の研削方法 | |
JPH07164025A (ja) | 圧延ロールの研削方法および装置 | |
JP4453299B2 (ja) | 表面欠陥の少ない鋼帯の製造方法 | |
JPH09196649A (ja) | ロール状回転体の摩耗劣化診断方法 | |
JP2005279889A (ja) | 金属鋼帯のオンライン欠陥除去装置及びその欠陥除去方法 | |
JP3777719B2 (ja) | オンラインロールグラインダによる圧延ロール表面の研削方法 | |
JPH08132339A (ja) | オンライン圧延ロール研削方法及び装置 | |
CN116237359A (zh) | 棒线材轧机转速控制方法及装置、计算机可读介质 | |
JP2003311592A (ja) | 研削量予測によるロール研削方法 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
ENP | Entry into the national phase |
Ref document number: 2021559210 Country of ref document: JP Kind code of ref document: A |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21864033 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 202317011780 Country of ref document: IN |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 21864033 Country of ref document: EP Kind code of ref document: A1 |