WO2022215458A1 - 鋼管の真円度予測モデルの生成方法、真円度予測方法、真円度制御方法、製造方法、及び真円度予測装置 - Google Patents
鋼管の真円度予測モデルの生成方法、真円度予測方法、真円度制御方法、製造方法、及び真円度予測装置 Download PDFInfo
- Publication number
- WO2022215458A1 WO2022215458A1 PCT/JP2022/011604 JP2022011604W WO2022215458A1 WO 2022215458 A1 WO2022215458 A1 WO 2022215458A1 JP 2022011604 W JP2022011604 W JP 2022011604W WO 2022215458 A1 WO2022215458 A1 WO 2022215458A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- roundness
- steel pipe
- pipe
- press
- prediction model
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 829
- 238000004519 manufacturing process Methods 0.000 title claims description 82
- 230000008569 process Effects 0.000 claims abstract description 742
- 229910000831 Steel Inorganic materials 0.000 claims abstract description 606
- 239000010959 steel Substances 0.000 claims abstract description 606
- 238000004364 calculation method Methods 0.000 claims abstract description 84
- 238000010801 machine learning Methods 0.000 claims abstract description 29
- 238000003825 pressing Methods 0.000 claims description 157
- 238000005452 bending Methods 0.000 claims description 64
- 230000009467 reduction Effects 0.000 claims description 55
- 238000012545 processing Methods 0.000 claims description 20
- 238000003066 decision tree Methods 0.000 claims description 12
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 238000005304 joining Methods 0.000 claims description 5
- 238000007637 random forest analysis Methods 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 description 78
- 238000003466 welding Methods 0.000 description 71
- 239000000463 material Substances 0.000 description 32
- 238000009826 distribution Methods 0.000 description 30
- 238000000465 moulding Methods 0.000 description 30
- 238000010586 diagram Methods 0.000 description 27
- 230000006399 behavior Effects 0.000 description 21
- 230000007246 mechanism Effects 0.000 description 20
- 230000000694 effects Effects 0.000 description 17
- 230000007423 decrease Effects 0.000 description 13
- 230000006870 function Effects 0.000 description 11
- 238000007689 inspection Methods 0.000 description 11
- 230000000452 restraining effect Effects 0.000 description 9
- 238000005096 rolling process Methods 0.000 description 9
- 238000003860 storage Methods 0.000 description 9
- 238000006073 displacement reaction Methods 0.000 description 8
- 238000005259 measurement Methods 0.000 description 7
- 239000002994 raw material Substances 0.000 description 6
- 238000013459 approach Methods 0.000 description 5
- 230000001965 increasing effect Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 238000007906 compression Methods 0.000 description 4
- 230000006835 compression Effects 0.000 description 4
- 230000002093 peripheral effect Effects 0.000 description 4
- 238000011144 upstream manufacturing Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 239000012141 concentrate Substances 0.000 description 3
- 230000003028 elevating effect Effects 0.000 description 3
- 230000000704 physical effect Effects 0.000 description 3
- 239000002436 steel type Substances 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000013001 point bending Methods 0.000 description 2
- 238000005482 strain hardening Methods 0.000 description 2
- 230000003746 surface roughness Effects 0.000 description 2
- 239000013077 target material Substances 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 239000011324 bead Substances 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 230000008602 contraction Effects 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
- 238000002788 crimping Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000004141 dimensional analysis Methods 0.000 description 1
- 230000005489 elastic deformation Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000002844 melting Methods 0.000 description 1
- 230000008018 melting Effects 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification 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
- 230000003287 optical effect Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000009864 tensile test Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 238000005493 welding type Methods 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
- 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
- B21C37/00—Manufacture of metal sheets, bars, wire, tubes or like semi-manufactured products, not otherwise provided for; Manufacture of tubes of special shape
- B21C37/06—Manufacture of metal sheets, bars, wire, tubes or like semi-manufactured products, not otherwise provided for; Manufacture of tubes of special shape of tubes or metal hoses; Combined procedures for making tubes, e.g. for making multi-wall tubes
- B21C37/08—Making tubes with welded or soldered seams
- B21C37/0815—Making tubes with welded or soldered seams without continuous longitudinal movement of the sheet during the bending operation
-
- 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
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B17/00—Systems involving the use of models or simulators of said systems
- G05B17/02—Systems involving the use of models or simulators of said systems electric
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/17—Mechanical parametric or variational design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B21—MECHANICAL METAL-WORKING WITHOUT ESSENTIALLY REMOVING MATERIAL; PUNCHING METAL
- B21D—WORKING OR PROCESSING OF SHEET METAL OR METAL TUBES, RODS OR PROFILES WITHOUT ESSENTIALLY REMOVING MATERIAL; PUNCHING METAL
- B21D5/00—Bending sheet metal along straight lines, e.g. to form simple curves
- B21D5/004—Bending sheet metal along straight lines, e.g. to form simple curves with program control
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B21—MECHANICAL METAL-WORKING WITHOUT ESSENTIALLY REMOVING MATERIAL; PUNCHING METAL
- B21D—WORKING OR PROCESSING OF SHEET METAL OR METAL TUBES, RODS OR PROFILES WITHOUT ESSENTIALLY REMOVING MATERIAL; PUNCHING METAL
- B21D5/00—Bending sheet metal along straight lines, e.g. to form simple curves
- B21D5/01—Bending sheet metal along straight lines, e.g. to form simple curves between rams and anvils or abutments
- B21D5/015—Bending sheet metal along straight lines, e.g. to form simple curves between rams and anvils or abutments for making tubes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/14—Pipes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/18—Manufacturability analysis or optimisation for manufacturability
Definitions
- the present invention relates to a method for generating a roundness prediction model for a steel pipe after a pipe expansion step in a UOE steel pipe manufacturing process, a roundness prediction method, a roundness control method, a manufacturing method, and a roundness prediction device.
- a steel plate having a predetermined length, width, and thickness is press-formed into a U-shape, and then press-formed into an O-shape.
- a technique for manufacturing a steel pipe (so-called UOE steel pipe) is widely used in which the butt portions are welded to form a steel pipe, and the diameter is increased (so-called pipe expansion) to improve roundness.
- pipe expansion a technique for manufacturing a steel pipe
- UOE steel pipe there has been an increasing demand for steel pipes using thicker materials or higher strength materials than in the past, and at the same time, the required precision for the roundness of steel pipes is also increasing.
- Patent Document 1 in a UOE steel pipe manufacturing process including a C-pressing process (end bending process), a U-pressing process (U-bending process), and an O-pressing process (O-bending process), the C-pressing process
- end bending process end bending process
- U-bending process U-pressing process
- O-bending process O-bending process
- Patent Document 2 peaking is achieved by setting the ratio between the outer diameter of the die used in the pipe expansion process that constitutes the manufacturing process of UOE steel pipe before expansion and the product inner diameter of the steel pipe to be manufactured within a predetermined range.
- a method for improving the roundness of a steel pipe by reducing the amount of angulation of the steel pipe is described.
- Patent Document 3 describes that the width of the U-press tool used in the U-press process should be 70% or less of the outer diameter of the product for a steel pipe having a predetermined strength and size. According to the method described in Patent Document 3, the state of contact between the O-pressing die and the compact is optimized in the O-pressing process, and the roundness of the open tube after the O-pressing process is said to be improved.
- the method described in Patent Document 1 is insufficient to meet the roundness required for current UOE steel pipes, and cannot produce UOE steel pipes with good roundness. Moreover, it provides appropriate operating conditions for the C-pressing process and the U-pressing process, and does not predict the roundness of the steel pipe to be a product after the pipe-expanding process. On the other hand, with the method described in Patent Literature 2, it is difficult to achieve good roundness for thick and high-strength UOE steel pipes in view of the strength of the pipe expanding equipment.
- the UOE steel pipe manufacturing process includes a plurality of processes such as at least a U press process and an O press process in addition to the pipe expansion process.
- Patent Literature 2 does not take into consideration the influence of operating conditions in processes other than the pipe expansion process on the roundness of the steel pipe after the pipe expansion process. Therefore, it may not always be possible to improve the roundness of the steel pipe after the pipe expansion process.
- Patent Document 3 describes that by adjusting the width of the U press tool within a predetermined range, the roundness of the open pipe after the O press process is improved. It has been suggested that the circularity after the O-pressing process varies depending on the pressing process. However, since the roundness of UOE steel pipe products is affected by the operating conditions of a plurality of manufacturing processes including the pipe expansion process, there is room for improvement in improving the roundness of steel pipes. Moreover, the method described in Patent Document 3 does not predict the roundness of the steel pipe after the pipe expansion process.
- the present invention has been made in view of the above problems, and an object of the present invention is to provide a roundness prediction model for accurately predicting the roundness of a steel pipe after a pipe expansion process in a UOE steel pipe manufacturing process including a plurality of processes.
- a method for generating a steel pipe roundness prediction model capable of generating Another object of the present invention is to provide a steel pipe roundness prediction method and a roundness prediction device capable of accurately predicting the roundness of a steel pipe after a pipe expansion step in a UOE steel pipe manufacturing process including a plurality of steps. to provide.
- Another object of the present invention is to provide a method for controlling the roundness of a steel pipe and a method for producing a UOE steel pipe with good roundness.
- the method for generating a steel pipe roundness prediction model comprises a U-pressing step of forming a steel plate into a U-shaped cross-section compact using a U-press tool, and forming the U-shaped cross-section compact into an open pipe.
- a steel pipe manufacturing process including an O-pressing step of processing and a pipe expanding step of performing forming processing by pipe expansion on a steel pipe in which the width direction ends of the open pipe are joined, the roundness of the steel pipe after the pipe expansion step is measured.
- a method for generating a steel pipe roundness prediction model to be predicted comprising: one or more operation parameters selected from the operation parameters of the U-press process and one selected from the operation parameters of the O-press process Numerical calculation including an operating condition data set including the above operating parameters as input data and using the roundness information of the steel pipe after the pipe expansion process as output data, and executing the numerical calculation a plurality of times while changing the operating condition data set.
- the basic data acquisition step preferably includes a step of calculating roundness information of the steel pipe after the pipe expansion process from the operating condition data set using the finite element method.
- the roundness prediction model preferably includes one or more parameters selected from the attribute information of the steel plate as the operating condition data set.
- the roundness prediction model may include, as the operating condition data set, one or more parameters selected from the operating parameters of the pipe expanding process.
- the manufacturing process of the steel pipe includes a C-pressing process of forming by bending the ends of the steel sheet in the width direction prior to the U-pressing process, and the roundness prediction model is the operating condition data set. It may include one or more operating parameters selected from the operating parameters of the C-press process.
- the operating parameters of the U-press process may include one or more operating parameters of the shape information of the U-press tool, the amount of U-press reduction, the initial U-press support interval, and the final U-press support interval.
- machine learning it is preferable to use machine learning selected from neural network, decision tree learning, random forest, Gaussian process regression, and support vector regression.
- the operating conditions of the steel pipe manufacturing process are used as inputs for the steel pipe roundness prediction model generated by the steel pipe roundness prediction model generation method according to the present invention. and inputting the operating condition data set obtained in the operating parameter obtaining step into the roundness prediction model to obtain the operating condition data set set as and a roundness prediction step of predicting roundness information.
- a steel pipe roundness control method uses the steel pipe roundness prediction method according to the present invention to select a process to be reset from among a plurality of forming processes constituting the steel pipe manufacturing process. Before the start of, predicting the roundness information of the steel pipe after the pipe expansion process, and based on the predicted roundness information of the steel pipe, at least one or more selected from the operation parameters of the process to be reset or one or more operation parameters selected from the operation parameters of the forming process downstream of the process to be reset.
- a steel pipe manufacturing method includes a step of manufacturing a steel pipe using the steel pipe roundness control method according to the present invention.
- a steel pipe roundness prediction apparatus includes a U-pressing process for processing a steel plate into a U-shaped cross-section compact using a U-press tool, and an O-pressing process for processing the U-shaped cross-section compact into an open pipe.
- the roundness of a steel pipe for predicting the roundness of the steel pipe after the pipe expansion step in a steel pipe manufacturing process including a pipe expansion step in which a steel pipe formed by joining the ends of the open pipe in the width direction is formed by pipe expansion.
- operating condition data including one or more operating parameters selected from the operating parameters of the U-press process and one or more operating parameters selected from the operating parameters of the O-press process.
- a basic data acquisition unit that generates a plurality of sets of data for roundness information of the steel pipe after the pipe expansion process as learning data
- a circularity prediction model generation unit that generates a circularity prediction model using machine learning, with the condition data set as input data and the circularity information of the steel pipe after the pipe expansion process as output data, and the operating conditions of the steel pipe manufacturing process.
- an operation parameter acquisition unit that acquires online the operating condition data set set as the operation parameter acquisition unit using the roundness prediction model generated in the roundness prediction model generation unit.
- a roundness prediction unit that predicts on-line roundness information of the steel pipe after the pipe expansion process corresponding to the condition data set.
- a terminal device having an input unit that acquires input information based on a user's operation and a display unit that displays the roundness information, and the operation parameter acquisition unit is based on the input information acquired by the input unit. to update part or all of the operating condition data set in the manufacturing process of the steel pipe, and the display unit displays the trueness of the steel pipe predicted by the roundness prediction unit using the updated operating condition data set. Circularity information should be displayed.
- a roundness prediction model is generated that accurately predicts the roundness of a steel pipe after a pipe expansion step in a UOE steel pipe manufacturing process including multiple steps. can do.
- the steel pipe roundness prediction method and the roundness prediction device according to the present invention it is possible to accurately predict the roundness of a steel pipe after a pipe expansion step in a UOE steel pipe manufacturing process including a plurality of steps. can.
- a UOE steel pipe having good roundness can be manufactured.
- FIG. 1 is a diagram showing a manufacturing process of a steel pipe that is one embodiment of the present invention.
- FIG. 2 is a perspective view showing the overall configuration of the C press device.
- FIG. 3 is a schematic diagram showing the configuration of the press mechanism shown in FIG.
- FIG. 4 is a schematic diagram showing the overall configuration of the U press device.
- FIG. 5 is a schematic diagram for explaining the operation of the U press device.
- FIG. 6 is a schematic diagram showing a modification of the U press device.
- FIG. 7 is a schematic diagram for explaining the O-pressing process.
- FIG. 8 is a schematic diagram showing the configuration of a tube expanding device.
- FIG. 9 is a diagram for explaining a method of measuring the outer diameter shape of a steel pipe.
- FIG. 9 is a diagram for explaining a method of measuring the outer diameter shape of a steel pipe.
- FIG. 10 is a block diagram showing the configuration of a generating apparatus for a steel pipe roundness prediction model according to an embodiment of the present invention.
- 11 is a block diagram showing the configuration of the roundness offline calculator shown in FIG. 10.
- FIG. 12 is a diagram showing an example of the relationship between pipe thickness and pipe expandability for each yield stress of a steel pipe.
- FIG. 13 is a diagram showing an example of the relationship between the pipe thickness for each outer diameter of a steel pipe and the pipe expandability.
- FIG. 14 is a diagram showing an example of measurement of the cross-sectional shape of a steel pipe before the pipe expansion process.
- FIG. 15 is a diagram showing the relationship between the tube expansion ratio and peaking in the three projections shown in FIG. 14.
- FIG. FIG. 16 is a diagram for explaining the definition of peaking.
- FIG. 17 is a diagram for explaining the shape of the U press tool.
- FIG. 18 is a diagram for explaining a steel pipe roundness control method according to an embodiment of the present invention.
- FIG. 19 is a diagram showing the configuration of a steel pipe roundness prediction apparatus that is an embodiment of the present invention.
- FIG. 20 is a diagram showing an example of a finite element model in the O press process.
- FIG. 1 is a diagram showing the manufacturing process of a steel pipe that is one embodiment of the present invention.
- a thick steel plate manufactured by a thick plate rolling process which is a pre-process of the steel pipe manufacturing process, is used as a raw steel plate.
- a representative thick steel plate has a yield stress of 245 to 1050 MPa, a tensile strength of 415 to 1145 MPa, a thickness of 6.4 to 50.8 mm, a width of 1200 to 4500 mm, and a length of 10 to 18 m.
- the steel plate which is the raw material, is first machined in the pretreatment process. Specifically, in order to adjust the width of the steel sheet within a predetermined range, the width direction end portion of the steel sheet is cut or cut by a width processing device. As a result, the outer diameter of the steel pipe formed into the UOE steel pipe falls within the range required as a product. Further, the width direction end portions of the steel plate are cut or fused in advance into a chamfered shape called a bevel by a bevel processing device. This is to ensure the strength of the welded portion by facilitating the flow of the molten metal in the thickness direction of the welded portion in the subsequent welding process.
- the end bending of the steel plate (also referred to as crimping) is performed using a C press machine as the C press process.
- a C press machine As the C press process, the steel plate is formed into a U-shaped molded body (a molded body having a U-shaped cross section) using a U-press device.
- the U-shaped molded body is subjected to an O-pressing process using an O-pressing device to reduce the seam gap and form an open tube having a generally tubular cross section. be.
- the seam gaps formed at the ends of the open pipe in the width direction are constrained so that the ends in the width direction are in contact with each other, and the ends in the width direction are held together. It is a process of joining by a welding device. As a result, the open pipe becomes a steel pipe in which the ends in the width direction are joined together.
- a tube expansion device having a plurality of tube expansion tools having curved surfaces obtained by dividing a circular arc into a plurality of sections is used to bring the curved surfaces of the tube expansion tools into contact with the inner surface of the steel pipe. This is the process of expanding the pipe.
- the steel pipes manufactured in this manner are judged whether or not the quality of the material, appearance, dimensions, etc., satisfies predetermined specifications. Shipped.
- the inspection process includes a roundness measuring process of measuring the roundness of the steel pipe using a roundness measuring machine.
- FIG. 2 is a perspective view showing the overall configuration of the C press device.
- the C press device 10 includes a conveying mechanism 11 that conveys the steel sheet S in the conveying direction along the longitudinal direction thereof, and one width direction end of the steel sheet S with the conveying direction downstream side of the steel sheet S as the front.
- a press mechanism 12A that bends Sc to a predetermined curvature
- a press mechanism 12B that bends the other widthwise end portion Sd to a predetermined curvature
- left and right presses according to the width of the steel plate S to be subjected to end bending A gap adjusting mechanism (not shown) for adjusting the gap between the mechanisms 12A and 12B is provided.
- the conveying mechanism 11 is composed of a plurality of rotationally driven conveying rolls 11a arranged before and after the press mechanisms 12A and 12B, respectively.
- symbol Sa in a figure has shown the front-end
- FIG. 3(a) shows a cross section in the width direction of the press mechanism 12A that bends one width direction end Sc of the steel plate S, viewed from the upstream side in the conveying direction of the steel plate S toward the downstream side in the conveying direction.
- the press mechanism 12A and the press mechanism 12B are symmetrical and have the same configuration.
- the press mechanisms 12A and 12B include an upper die 13 and a lower die 14 as a pair of dies arranged opposite to each other in the vertical direction, and the lower die 14 together with the tool holder 15 are pushed up (in a direction approaching the upper die 13). ) and a hydraulic cylinder 16 as a mold moving means for clamping the mold with a predetermined press force.
- the press mechanisms 12A and 12B include a clamp mechanism 17 that releasably clamps the steel plate S inside the upper mold 13 and the lower mold 14 in the width direction.
- the longitudinal length of the steel plate S of the upper mold 13 and the lower mold 14 is usually shorter than the length of the steel plate S.
- the end bending process is performed a plurality of times while intermittently feeding the steel plate S in the longitudinal direction by the conveying mechanism 11 (see FIG. 2).
- the lower die 14 in contact with the outer surfaces in the bending direction of the width direction ends Sc and Sd of the steel plate S to be bent has a pressing surface 14a facing the upper die 13 .
- the upper mold 13 has a convex molding surface 13a facing the pressing surface 14a and having a radius of curvature corresponding to the inner diameter of the steel pipe to be manufactured.
- the pressing surface 14a has a concave surface shape that approaches the upper die 13 as it goes outward in the width direction.
- the pressing surface 14a of the lower mold 14 is concavely curved, it may be a surface that approaches the upper mold 13 toward the outside in the width direction, and may be an inclined flat surface.
- an appropriate shape is designed according to the thickness, outer diameter, etc. of the steel plate S, and may be appropriately selected and used according to the target material. .
- FIG. 3(b) is a cross-sectional view in the width direction of the press mechanism 12A at the same position as in FIG. 3(a), but shows a state in which the lower die 14 is pushed up by the hydraulic cylinder 16 and clamped.
- the lower mold 14 is pushed up by a hydraulic cylinder 16 , and the widthwise end Sc of the steel plate S is bent into a shape along the arc-shaped molding surface 13 a of the upper mold 13 .
- the width of the end bending process (width of end bending) varies depending on the width of the steel sheet S, but is generally about 100 to 400 mm.
- Fig. 4 shows the overall configuration of the U-press device for executing the U-press process.
- U-press devices There are various kinds of U-press devices, but a typical example is shown.
- an elevating cylinder 21 is attached to the upper part of a machine frame 20 with the upper rod facing down.
- the upper end of member 23 is attached.
- a sliding cylinder 26 is installed in the center of the lower floor surface 24 of the machine frame 20 so that the rod 25 faces the inside of the machine frame 20, and a pair of left and right sliding blocks 27 are provided on the sides of the sliding cylinder 26. is installed.
- a saddle (pedestal) 28 is attached to the head of the rod 25 of the sliding cylinder 26 .
- the rod 25 and the sliding block 27 are connected by a link 29 .
- the link 29 has a rotation center 30 fixed to the slide block 27, and a brake roll (U-bending support) 32 for bending the steel plate S is attached to the tip of an arm 31 extending therefrom.
- the steel sheet S which is the material for the U-pressing process, is a steel sheet that has undergone end bending in the above-described C-pressing process. However, a steel plate that has not been subjected to end bending by the C press process may be used.
- the steel plate S is placed on the left and right brake rolls 32 so that the horizontal direction of the U press shown in FIG. At that time, the steel plates S are installed approximately bilaterally symmetrical with respect to the center of the left and right brake rolls 32 .
- FIG. 5 shows a state in which the U-press tool 22 is lowered to the preset lowest position by the elevating cylinder 21 .
- the U-press tool 22 is lowered by the lifting cylinder 21
- the steel plate S comes into contact with the saddle 28, and the rod 25 is lowered by the saddle 28.
- the link 29 closes and the sliding block 27 moves to the center side of the machine frame 20, the arm 31 rises, and the left and right brake rolls 32 move in the direction to close the space therebetween.
- the brake roll 32 approaches from the side surface side of the steel sheet S formed into a U-shape, and the steel sheet S is processed into a U-shaped formed body.
- the tip shape of the U-press tool 22 ( An appropriate shape is selected as the shape of the range in contact with the steel plate S).
- the larger the U-press reduction amount of the U-press tool 22 the amount of pressing from the position where the U-press tool 22 abuts on the upper surface of the steel plate S to the lowest position
- the shape of the region of the U-shaped molded body in contact with the U-press tool 22 approaches the shape of the tip of the U-press tool 22 .
- the interval between the left and right brake rolls 32 (U-press support initial interval) can be set.
- the height of the saddle 28 or the length of the rod 25 the height position at which the steel plate S contacts the saddle 28 when the U-press tool 22 is processed is changed.
- the opening/closing position of the link 29 is changed, and the position of the brake roll 32 during forming and the gap between the left and right brake rolls 32 when the U-press tool 22 reaches the lowest position (final U-press support gap) are changed. Change. As a result, the opening amount of the opening of the U-shaped molded body changes. Therefore, when executing the U press process, these operation parameters are appropriately set according to the thickness and steel type of the steel plate S and the target outer diameter of the steel pipe.
- the U-press device shown in FIGS. 4 and 5 is of a type in which the brake rolls 32 are moved in a direction to close the distance between them by the link 29, and is called a Kaiser-type U-press device.
- a U-press apparatus called a Burson-type U-press apparatus shown in FIG.
- the functions of the saddle 28 and the brake roll 32 in the Kaiser type U press machine shown in FIGS. is provided in the lower die (rocker die) 35.
- left and right rocker dies 35 rotate around a rotation fulcrum 36 .
- Reference numeral 38 in FIG. 6 denotes a member called a cushion, which is used to prevent the steel sheet S from suddenly falling during forming and to raise the U-shaped formed body after forming. .
- the tip shape of the U-pressing tool 37 is selected according to the thickness and steel type of the steel plate S and the target outer diameter of the steel pipe, and the U-pressing reduction amount is set. be done.
- the U-press support initial interval can be set by changing the set positions of the left and right rocker dies 35 .
- the U-press support final spacing can be varied by setting the initial height of the saddle portion 33 (or the initial angle of the rocker die 35). Therefore, in the U-press process, the operating conditions of the U-press process can be specified by the same operating parameters regardless of which U-press apparatus is used.
- the U press machine shown in FIG. 6 has a bilaterally symmetrical structure. indicates the state in which the U press tool 37 has descended to the preset lowest position.
- FIG. 7 schematically shows how the U-shaped compact is deformed in the O-pressing process.
- the U-shaped compact is placed on the lower die 40 of the O-pressing device.
- the semi-circular upper die 41 whose lower side is open is lowered, the initial state before the O-pressing step shown in FIG. 7(a) is obtained.
- the upper die 41 is lowered by a die lifting device (not shown), as shown in FIG. 7(b)
- the U-shaped compact becomes a cylinder having a substantially circular cross section along the upper and lower dies. .
- the U-shaped molded body changes from the substantially circular state shown in FIG. Elastically recovers to return to shape.
- the shape of the U-shaped compact after the O-pressing process is slightly elongated and elliptical as shown in FIG. 7(c). This state is called an open tube.
- the operation parameters to be set when executing the O press process are the uppermost part of the inner surface of the upper die 41 when the upper die 41 is lowered to its lowest position shown in FIG. can be specified using the distance between (referred to as the O press reduction amount). Alternatively, it may be specified by the gap between the lowermost portion of the upper die 41 and the uppermost portion of the lower die 40 when the upper die 41 is lowered to its lowest position (referred to as an O press reduction position) as shown in FIG. 7(b).
- the compression rate in the O-pressing process is determined by W representing the width of the steel sheet S before the start of the U-pressing process, It is defined as (WL)/W ( ⁇ 100%), where L is the thickness (the portion where the die contacts the steel plate S and the portion where the gap between the upper die 41 and the lower die 40 is added).
- the O press die radius which is the radius of curvature of the curved surfaces of the upper die 41 and the lower die 40 in contact with the U-shaped compact, may be used as an operation parameter for the O press process.
- the U-shaped compact When the U-shaped compact is placed on the lower die 40, it is usually left-right symmetrical so that the lowest point of the U-shaped cross section coincides with the lowest point on the inner surface side of the lower die 40.
- the position where the U-shaped molded body is placed may be shifted.
- the open pipes formed in the O-pressing process are then abutted against each other at the end faces of the openings, and the end faces are welded by a welding machine (joining means) to form a steel pipe.
- a welding machine for example, one configured by three types of welding machines, ie, a tack welding machine, an inner surface welding machine, and an outer surface welding machine, is used.
- the tack welder continuously brings the butted end faces into close contact with each other with cage rolls in an appropriate positional relationship, and tack welds the contact portion over the entire length in the pipe axial direction.
- the tack-welded steel pipe is welded from the inner surface of the butt portion (submerged arc welding) by an inner surface welder, and further welded from the outer surface of the butt portion by an outer surface welder (submerged arc welding).
- FIGS. 8A to 8C are diagrams showing configuration examples of a tube expansion device.
- the tube expansion device includes a plurality of tube expansion dies 51 having curved surfaces obtained by dividing a circular arc into a plurality of parts along the circumferential direction of a tapered outer peripheral surface 52 .
- the pull rod 53 is retracted from the tube expansion start position to perform the first tube expansion process.
- the pipe expansion dies 51 that are in sliding contact with the taper outer peripheral surface 52 are displaced in the radial direction due to the wedge action, and the steel pipe P is expanded. Then, the unevenness of the cross-sectional shape of the steel pipe P is reduced, and the cross-sectional shape of the steel pipe P becomes close to a perfect circle.
- the pull rod 53 is advanced to the tube expansion start position, and the tube expansion die 51 is returned to the inner side in the axial vertical direction by the release mechanism. move further. Then, after adjusting the tube expansion die 51 to a new tube expansion position, the above operation is repeated. Thereby, the pipe expansion process can be performed over the entire length of the steel pipe P by the pitch of the pipe expansion die 51 .
- the operating parameters that determine the operating conditions of the tube expansion process include the tube expansion rate, the number of tube expansion dies, the tube expansion die radius, and the like.
- the expansion rate refers to the ratio of the difference between the outer diameter of the steel pipe P after expansion and the outer diameter of the steel pipe P before expansion to the outer diameter of the steel pipe P before expansion.
- the outer diameter of the steel pipe P before and after expansion can be calculated by measuring the circumference of the steel pipe P.
- the tube expansion rate can be adjusted by the stroke amount when expanding the tube expansion die 51 in the radial direction.
- the number of tube expansion dies refers to the number of tube expansion dies at a portion that abuts on the steel pipe P arranged in the circumferential direction during tube expansion.
- the tube expansion die radius is the radius of curvature in the circumferential direction of the portion of each tube expansion die that contacts the steel pipe P.
- the expansion ratio is an operation parameter that can easily adjust the roundness after the pipe expansion process when the attribute values such as the yield stress and thickness of the steel plate used as the material fluctuate.
- the tube expansion ratio increases, the curvature of the region in contact with the tube expansion die is imparted uniformly according to the radius of the tube expansion die over the entire circumference, thereby improving the roundness.
- the greater the number of pipe expansion dies the more the steel pipe can be prevented from localized variations in curvature in the circumferential direction, so that the steel pipe has better roundness after the pipe expansion process.
- the upper limit of the expansion rate is restricted in order to keep the diameter of the product steel pipe within the specified dimensional tolerance. Further, if the expansion rate is too large, the gap between the expansion dies in the circumferential direction becomes large when the expansion dies are enlarged, which may impair the roundness of the steel pipe. Furthermore, in some cases, the portion softened by the heat during welding causes localized concentration of deformation, resulting in increased wall thinning at that portion, and the pipe thickness does not fall within the predetermined tolerance range. In addition, the Bauschinger effect can reduce the compressive yield strength of steel pipe products. It is necessary to consider that an upper limit is set. Therefore, in actual operation, the expansion rate is set so that the roundness of the steel pipe falls within a predetermined value at an expansion rate smaller than the preset upper limit of the expansion rate.
- the roundness measured in the roundness measuring process is an index that indicates the degree of deviation of the outer diameter shape of the steel pipe from the true circular shape. Normally, the closer the circularity is to zero, the closer the cross-sectional shape of the steel pipe is to a perfect circle.
- the roundness is calculated based on the outer diameter information of the steel pipe measured by a roundness measuring machine. For example, if a steel pipe is equally divided in the circumferential direction at an arbitrary pipe length position and the outer diameters at opposing positions are selected, and the maximum and minimum diameters are Dmax and Dmin, respectively, the roundness is Dmax- Dmin can be defined.
- the circularity of the steel pipe may be defined by the difference between the inner diameter and the inner diameter of the steel pipe based on the inner diameter of the steel pipe instead of the outer diameter of the steel pipe.
- the longitudinal position of the steel pipe whose roundness is measured can be arbitrarily selected.
- the roundness may be measured near the ends in the longitudinal direction of the steel pipe, or the roundness at the central portion in the longitudinal direction of the steel pipe may be measured.
- the roundness does not necessarily have to be based on the difference between the maximum diameter and the minimum diameter.
- An equivalent temporary perfect circle (diameter) having the same area as the inner area of the curve is calculated from a figure representing the outer diameter shape of the steel pipe in a continuous diagram, and the steel pipe is measured based on the temporary perfect circle. It may be defined as an image representing the outer diameter shape and the shifted region. This is because image information can be used as an output in machine learning, which will be described later.
- the following method can be used.
- an arm 60 that can rotate 360 degrees around the approximate center axis of the steel pipe P, displacement gauges 61a and 61b attached to the tip of the arm 60, and rotation of the arm 60 Using a device having a rotation angle detector 62 for detecting the rotation angle of the shaft, displacement gauges 61a and 61b detect the rotation center of the arm 60 and the outer circumference of the steel pipe P for each minute angular unit of rotation of the arm 60. The distance to the measurement point is measured, and the outer diameter shape of the steel pipe P is specified based on this measured value.
- a rotary arm 63 that rotates around the central axis of the steel pipe P, and a mount (not shown) provided on the end side of the rotary arm 63 so as to be movable in the radial direction of the steel pipe P.
- a pair of pressure rollers 64a and 64b that contact the outer and inner surfaces of the ends of the steel pipe P and rotate along with the rotation of the rotating arm 63, and a base that presses the pressure rollers 64a and 64b against the outer and inner surfaces of the steel pipe P.
- a pair of pressing air cylinders (not shown) fixed to the steel pipe based on the amount of radial movement of the frame and the pressing positions of the pressing rollers 64a and 64b by the pressing air cylinders.
- the prediction accuracy is verified by comparing the roundness prediction result by the roundness prediction model described later with the roundness measurement value obtained in the above inspection process. be able to. Therefore, for the prediction result of the roundness prediction model described later, it is possible to further improve the prediction accuracy of the roundness prediction model by adding the actual value of the prediction error to the prediction result of the roundness prediction model. be.
- FIG. 10 is a block diagram showing the configuration of a generation device for a steel pipe roundness prediction model, which is one embodiment of the present invention.
- FIG. 11 is a block diagram showing the configuration of the roundness offline calculator 112 shown in FIG.
- a steel pipe roundness prediction model generating apparatus 100 is configured by an information processing apparatus such as a workstation, and includes a basic data acquisition unit 110, a database 120, and a true model.
- a circularity prediction model generation unit 130 is provided.
- the basic data acquisition unit 110 obtains an operating condition data set 111 that quantifies the factors that affect the roundness of the steel pipe through the U-pressing process, the O-pressing process, the welding process, and the tube expanding process, and the operating condition data set 111.
- a circularity off-line calculator 112 that outputs circularity information after the tube expansion process as an input condition.
- the operating condition data set 111 includes at least operating parameters for the U-press process and operating parameters for the O-press process. This is because these factors have a large effect on the roundness of the steel pipe after the pipe expansion process, and influence the variation in the roundness.
- the attribute information of the steel sheet used as the material, the operating parameters of the C-pressing process, the operating parameters of the welding process, and the operating parameters of the tube expanding process may also be included. Data used for the operating condition data set 111 will be described later.
- the basic data acquisition unit 110 variously changes the parameters included in the operating condition data set 111 and performs numerical calculation by the roundness offline calculation unit 112, thereby obtaining the post-tube expansion process data corresponding to the plurality of operating condition data sets 111. Calculate the roundness information of the steel pipe.
- the range for changing the parameters included in the operating condition data set 111 may be determined based on the range that can be changed as normal operating conditions according to the size of the steel pipe to be manufactured and the specifications of equipment in each process.
- the roundness offline calculation unit 112 calculates the shape of the steel pipe after the pipe expansion process by numerical analysis corresponding to a series of manufacturing processes up to the steel pipe expansion process, and obtains roundness information of the steel pipe from the shape of the steel pipe after the pipe expansion process.
- the series of manufacturing processes includes a U press process, an O press process, and a tube expansion process.
- the roundness offline calculator 112 includes finite element model generators 112a to 112c and a finite element analysis solver 112d corresponding to each process.
- the roundness offline calculator 112 may include a finite element model generator corresponding to the C press process.
- finite element analysis solver 112d there are many commercially available general-purpose analysis software, so it is possible to utilize them by appropriately selecting and incorporating them. This is because if a finite element model corresponding to each process is generated, numerical analysis can be performed using a single finite element analysis solver.
- a finite element analysis solver 112d is mounted on a computer separate from the roundness off-line calculation unit 112, and input data including the finite element model and output data as calculation results are transferred to the computer on which the finite element analysis solver 112d is mounted. It may be a form of transmitting and receiving between.
- the finite element model generation units 112a to 112c of the roundness offline calculation unit 112 are installed in the client computer
- the finite element analysis solver 112d is installed in the server computer
- the input data including the finite element model and the It may be configured to transmit and receive calculation results regarding the shape of the steel pipe.
- the finite element method is a kind of approximate solution method that divides a continuum into a finite number of elements. Even though it is an approximate solution method, the finite element method seeks a solution that satisfies the force balance and continuity of displacement at the node of the element, and it is possible to obtain a highly accurate solution even if the deformation is uneven. can be done.
- the stress, strain, and displacement in an element are defined independently for each element, and are formulated as a problem of solving simultaneous equations by associating with the displacement (velocity) of a node. In this case, a method of evaluating strain (increase) and stress using the displacement (velocity) at the node of the element as an unknown is widely used.
- the finite element method is characterized by performing calculations based on the principle of virtual work expressed in integral form for the stress balance condition within the element.
- the accuracy of analysis results varies depending on conditions such as element division, and calculation time is also required.
- the finite element method is characterized by being able to obtain solutions to problems that are difficult to solve by other methods as solutions that satisfy the basic equations of plastic mechanics within nodes or elements. Therefore, it is possible to obtain solutions of the displacement, stress field, and strain field of the work piece that are close to actual phenomena even for complicated working histories in the steel pipe manufacturing process.
- a part of the finite element analysis solver 112d may be replaced with various numerical analysis methods such as the slip line field method and the energy method, and approximate solution methods. This makes it possible to shorten the overall calculation time.
- the finite element analysis used in the present embodiment is for executing elastic-plastic analysis, and does not include temperature field analysis such as heat conduction analysis. However, when the processing speed is high and the temperature of the steel sheet rises greatly due to the heat generated during processing, the analysis may be performed by coupling the heat conduction analysis and the elasto-plastic analysis.
- the elasto-plastic analysis of the present embodiment is a two-dimensional cross-sectional analysis for all of the U-pressing process, the O-pressing process, and the pipe expanding process.
- the attribute information of the steel plate which is the material to be processed in the U press process, is given as input data.
- the C-pressing process is included as a pre-process of the U-pressing process, as a result of performing a finite element analysis of the C-pressing process, the shape and stress/strain distribution of the obtained steel plate are different from those of the work material in the U-pressing process.
- Initial condition the U-press process finite element model generation unit 112a divides the inside of the steel sheet into elements based on the dimensions and shape of the steel sheet before the U-press process. Element division is performed automatically based on preset element division conditions.
- the distribution of stress and strain remaining inside may be assigned to each element based on the manufacturing history given to the steel sheet in the previous process. This is because, in the U-pressing process, which mainly involves bending, the initial residual stress may also affect the shape of the U-shaped formed body of the steel sheet after working.
- the calculation conditions in the U press process are sent as input data to the finite element analysis solver 112d.
- the calculation conditions in the U-press process include the operation parameters of the U-press process, as well as physical property values such as steel plates and tools, geometric boundary conditions, mechanical boundary conditions, etc. All boundary conditions are specified. shall contain all information necessary to perform a finite element analysis.
- the finite element analysis solver 112d performs numerical analysis under the calculation conditions given above to determine the shape of the U-shaped compact after the U-pressing process and the distribution of residual stress and strain inside. The results calculated in this manner are used as input data for the next O-pressing process in the roundness offline calculator 112 .
- the finite element model generator 112b for the O-pressing process divides the inside of the U-shaped compact into elements. Element division is performed automatically based on preset element division conditions. At this time, it is preferable to assign the distribution of stress and strain calculated for the previous step to each element.
- the calculation conditions in the O-pressing process are sent as input data to the finite element analysis solver 112d.
- the calculation conditions in the O-pressing process include the operating parameters of the O-pressing process, as well as the physical properties of the steel plate and tools, geometrical boundary conditions, mechanical boundary conditions, and other boundary conditions. shall contain all information necessary to perform a finite element analysis.
- the finite element analysis solver 112d performs numerical analysis under the calculation conditions given above, and obtains the shape of the open pipe after the O-pressing process and the distribution of stress and strain remaining inside. The results calculated in this manner are used as input data in the finite element model generator 112c for the next tube expansion process. At this time, in the welding process of welding the seam gap portion of the open pipe, the residual stress and strain generated in the welded steel pipe may also be obtained by numerical analysis of the welding process.
- the analytical solution of stress and strain for a curved beam based on beam theory should be replaced with the stress and strain inside the open pipe calculated by finite element analysis. may be superimposed on the distribution of to obtain the stress/strain distribution after the welding process. Thereby, the calculation time can be shortened.
- the finite element model generator 112c for the pipe expansion process divides the interior of the steel pipe into elements. Element division is performed automatically based on preset element division conditions. At this time, it is preferable to assign the stress and strain distributions calculated as described above to each element.
- the generated finite element model of the tube expansion process is sent to the finite element analysis solver 112d together with calculation conditions for the tube expansion process.
- the calculation conditions in the tube expansion process include the operation parameters of the tube expansion process of this embodiment, and in addition, all boundary conditions such as physical property values such as steel plates and tools, geometric boundary conditions and mechanical boundary conditions are specified. , shall contain all the information necessary to perform a finite element analysis.
- the finite element analysis solver 112d performs numerical analysis under the calculation conditions given above, and obtains the shape of the steel pipe after the pipe expansion process and the distribution of internal stress and strain.
- the calculated shape of the steel pipe has a non-uniform curvature distribution in the circumferential direction, and the roundness of the steel pipe is obtained according to the definition of roundness in the roundness measurement step.
- the numerical analysis using the finite element method by the roundness offline calculator 112 may require approximately 1 to 10 hours of calculation time for one operating condition data set (one case). However, since the processing is executed off-line, there is no constraint on computation time.
- a plurality of computers may be used to perform numerical calculations corresponding to a plurality of operating condition data sets in parallel. This makes it possible to construct a database for generating a roundness prediction model in a short period of time. Furthermore, in recent years, computation using a GPGPU has reduced the computation time per case to about 1/2 to 1/10 of that in the past, and such a computer tool may also be used.
- the database 120 stores an operating condition data set 111 and corresponding data on the roundness of the steel pipe after the pipe expansion process.
- the data stored in database 120 can be obtained offline. Unlike a database that is accumulated as actual values of actual operation, it is possible to arbitrarily set an operating condition data set, so that statistical bias is unlikely to occur in the operating conditions set by the operating condition data set 111, and machine learning database suitable for In addition, since the results of calculations by strict numerical analysis are accumulated and not learning data that fluctuates over time, the more data accumulated, the more useful the database can be obtained. In addition, since the database 120 generated by off-line calculation can determine the roundness under conditions different from the actual manufacturing specifications, it is possible to predict the roundness in a range with no manufacturing record.
- the roundness prediction model generation unit 130 generates a post-tube expansion process for the input operating condition data set 111 based on the relationship between the plurality of sets of operating condition data sets 111 stored in the database 120 and the roundness information of the steel pipe.
- a roundness prediction model M learned by machine learning is generated to obtain information on the roundness of the steel pipe.
- the relationship between the operating conditions in each process and the roundness information of the steel pipe after the pipe expansion process may show complex nonlinearity, and modeling using the influence coefficient assuming a first-order linearity has low accuracy.
- machine learning methods using functions with nonlinearity such as neural networks enable highly accurate prediction.
- modeling means replacing the input/output relationship in numerical calculation with an equivalent functional form.
- the number of data required to generate the roundness prediction model M varies depending on the manufacturing range of the size of the steel pipe to be manufactured, it is sufficient if there are 200 or more pieces of data. Preferably 500 or more, more preferably 2000 or more data are used.
- a known learning method may be applied as the machine learning method.
- machine learning for example, a known machine learning technique using neural networks including deep learning, convolutional neural networks (CNN), recurrent neural networks (RNN), and the like may be used. Other methods include decision tree learning, random forest, Gaussian process regression, support vector regression, k-nearest neighbor method, and the like.
- an ensemble model combining a plurality of models may be used.
- the roundness prediction model M is generated offline, but the roundness prediction model generation unit 130 is incorporated into an online control system, and periodically calculated using a database that is calculated and accumulated offline at any time. The roundness prediction model may be updated at .
- the roundness prediction model M of the steel pipe after the pipe expansion process generated as described above has the following characteristics. That is, in the U-pressing process, the U-press tool is brought into contact with the vicinity of the center of the steel sheet in the width direction, and the steel sheet S is processed so as to wind around the tip of the U-press tool. In this case, since the bending moment applied to the steel plate differs depending on the contact position with the U-press tool, bending deformation having a curvature distribution occurs. Also, the shape of the tip of the U-press tool may have a shape in which curves having a plurality of curvatures are connected, and in this case also, the curvature of the steel plate changes along the surface of the U-press tool.
- shape information of the U-press tool is called shape information of the U-press tool.
- the bending moment acting on a so-called "curved beam” changes depending on the curvature of the beam.
- the bending moment applied in the O-pressing process is distributed according to the local curvature distribution of the steel sheet applied in the pressing process.
- deformation called "plastic hinge” in which bending strain concentrates locally may occur in a portion where the bending moment is large.
- the compressive force and bending moment applied to the U-shaped molded body in the O-pressing process vary depending on the opening amount of the widthwise end of the U-shaped molded body.
- the deformation state of the U-shaped molded body differs in the O-pressing process, and the curvature distribution along the circumferential direction in the formed open pipe also differs, which affects the roundness of the steel pipe after the pipe expansion process.
- the load in the pipe expansion process is proportional to the pipe thickness x the yield stress of the steel pipe, and the load in the pipe expansion process (pipe expansion load) increases for thick steel pipes and steel plates with high yield stress.
- the strength of the pipe expansion equipment tends to decrease in inverse proportion to the outer diameter of the pipe expansion tool. tend to decline.
- the ability to improve the roundness of steel pipes in the pipe expansion process tends to decrease as the load in the pipe expansion process approaches the strength of the equipment. Sometimes you can't. Therefore, it is preferable to optimize the operation parameters of both the U press process and the O press process to improve the roundness of the steel pipe after the pipe expansion process. It should include operating parameters for both processes.
- pipe expansion capacity the ability to improve the roundness of the steel pipe in the pipe expansion process
- tube expansion load the ratio of the equipment strength of the pipe expansion equipment to the pipe expansion load (tube expansion load). This is an index representing the allowance of the equipment with respect to the load required for pipe expansion, and the larger the value, the higher the pipe expansion capacity.
- the strength of the pipe expansion equipment is generally inversely proportional to the outer diameter of the steel pipe
- the pipe expansion load is proportional to the pipe thickness x the yield stress of the steel pipe. decrease when As a specific example of the pipe expansion capacity, the relationship between the outer diameter, pipe thickness, and yield stress is illustrated in Figs. do. FIG.
- FIG. 12 shows the relationship between pipe thickness and pipe expandability for each yield stress for a steel pipe with an outer diameter of 914.4 mm.
- the pipe expandability decreases as the pipe thickness increases, and decreases as the yield stress increases for the same pipe thickness.
- the steel pipe has a yield stress of 400 to 800 MPa and a pipe thickness of 19 to 55 mm. More preferably, the yield stress is 500-800 MPa and the tube thickness is 25-55 mm.
- FIG. 13 is a diagram showing the relationship between pipe thickness and pipe expandability for steel pipes with a yield stress of 300 MPa for each outer diameter.
- the tube expandability decreases as the tube thickness increases, and decreases as the outer diameter decreases for the same tube thickness.
- the steel pipe has an outer diameter of 16 to 48 inches and a pipe thickness of 12 to 55 mm. More preferably, the steel pipe has an outer diameter of 16 to 36 inches and a pipe thickness of 19 to 55 mm.
- the roundness prediction model M preferably includes one or more parameters selected from the attribute information of the steel plate.
- attribute information of a steel plate for example, the yield stress and thickness are subject to a certain amount of variation when manufacturing the steel plate used as the raw material. , the curvature after unloading will be affected by these parameters. That is, by including parameters that affect the deformation state during bending of the steel plate as the attribute information of the steel plate, it is possible to individually consider the influence of the yield stress and thickness of each material on the roundness.
- the O pressing process is also a process in which a bending force and a compressive force are applied using a die. It is preferable to use it as an input parameter of the prediction model M.
- the input of the roundness prediction model M include one or more operational parameters selected from the operational parameters of the tube expanding process. More preferably, the expansion rate is used as an operating parameter for the expansion process. This is because even in the process of manufacturing UOE steel pipes made from high-strength steel sheets, the expansion ratio in the pipe expansion process has a great effect on the final roundness of the product. However, if the pipe expansion rate can only be set within a narrow range due to the pipe expansion capacity of the pipe expansion equipment, etc., it is not necessarily included in the input of the roundness prediction model M because the range that can be changed as an operation parameter is narrow.
- the roundness prediction model M it is preferable to include one or more operational parameters selected from the operational parameters of the C press process as an input to the roundness prediction model M.
- the range in which the steel plate is bent in the C press process is limited to the vicinity of the width direction end of the steel plate, but does not necessarily match the region in which the bending deformation is applied in the U press process and the O press process. is. Therefore, by using the operation parameters in these forming processes, the roundness prediction accuracy of the steel pipe after the pipe expansion process is improved.
- FIG. 14 is a diagram showing the measurement results of the cross-sectional shape of the steel pipe before the pipe expansion process. In addition, since the weld bead portion is built up, the measurement results of that portion are excluded in the figure.
- a U-press tool with a punch width r (curvature radius of the side surface of the U-press tool 22 shown in FIG. 17) of 178 mm was selected for molding.
- the cross section of the steel pipe has a convex shape. Furthermore, when the O-pressing process is performed on such a steel plate in the U-pressing process, local bending deformation concentrates in a part of the steel plate, and plastic deformation occurs in the 2 o'clock direction (position B) of the steel pipe cross section shown in FIG. A local convex shape may occur due to the hinge.
- Peaking means that, as shown in FIG. 16, in the cross section of the steel pipe after the pipe expansion process, in a section of a predetermined distance (150 mm in this case) as the length of the chord, the outer peripheral surface of the steel pipe P and the chord is an index defined by the distance between an arc P1 corresponding to the outer diameter of a steel pipe and passing through both ends of the .
- the peaking is defined as positive when positioned on the convex side of an arc corresponding to the outer diameter of the steel pipe, and negative when positioned on the concave side. In other words, if the peaking value is 0, it means that the point is on an arc corresponding to the outer diameter of the steel pipe. It can be said that there is.
- FIG. 15 shows the results of examining the peaking after expanding the steel pipe, focusing on the three projections A1, A2, and B shown in FIG.
- the horizontal axis of FIG. 15 represents the expansion rate, which is an operational parameter of the tube expansion process
- the vertical axis represents peaking (Body PK) values.
- the protrusions A1 and A2 generated in the U-pressing process tend to decrease as the tube expansion rate increases, but the decrease is gradual.
- the peaking value of the protrusions B generated in the O-pressing process tends to decrease as the expansion ratio increases.
- the cross-sectional shape formed in the U-pressing process and the cross-sectional shape formed in the O-pressing process differ in the peaking decrease behavior with respect to the tube expansion rate in the tube expanding process. Therefore, in order to improve the roundness, it is necessary to appropriately set operating conditions in each molding process.
- the roundness prediction model of the present embodiment can take into consideration the influence of such operational parameters of a plurality of manufacturing processes on the roundness of the steel pipe after the pipe expansion process, and can predict the roundness with high accuracy. It becomes possible. In addition, since a roundness prediction model learned by machine learning is generated in advance, it is possible to immediately calculate the roundness as an output even if the input condition variables are changed, so it can be used online. Even in such a case, the operating conditions can be set and corrected immediately. Each parameter used for inputting the roundness prediction model will be described below.
- the attribute information of the steel plate used as the input data for the roundness prediction model M includes the yield stress, tensile strength, modulus of longitudinal elasticity, thickness, thickness distribution in the plate surface, and yield stress in the thickness direction of the steel plate.
- Any parameter that affects the roundness of the steel pipe after the expansion process can be used, such as distribution, magnitude of the Bauschinger effect, and surface roughness.
- the yield stress of the steel sheet, the distribution of the yield stress in the thickness direction of the steel sheet, and the thickness of the steel sheet directly affect the state of stress and strain in bending.
- tensile strength affects the state of stress during bending deformation.
- the Bauschinger effect influences the yield stress and subsequent work hardening behavior when the load due to bending deformation is reversed, and influences the stress state during bending deformation.
- the modulus of longitudinal elasticity of the steel sheet affects the springback behavior after bending.
- the thickness distribution in the plate surface changes the bending curvature distribution in the U-pressing process, and the surface roughness affects the friction state between the die and the steel plate in the O-pressing process. affect the degree.
- the yield stress, representative plate thickness, thickness distribution information, and representative plate width correspond to the information measured in the quality inspection process of the plate rolling process, which is the manufacturing process of the steel plate that is the raw material, and affect the deformation behavior in the U press process and O press process, and the steel pipe after the pipe expansion process. This is because it affects the roundness. This is also because the attribute information represents variation for each steel plate that is the material.
- the yield stress corresponds to information that can be obtained from a tensile test of a small test piece for quality confirmation taken from a thick steel plate as a material, and can be used as a representative value within the surface of the steel plate as a material.
- the representative plate thickness is the thickness that represents the in-plane thickness of the steel plate as a material, and is the average thickness of the thickness at the center in the width direction of the steel plate at any position in the longitudinal direction of the steel plate and the thickness in the longitudinal direction. value may be used.
- the representative plate thickness may be the average value of the thickness of the entire surface of the steel plate.
- the thickness distribution information refers to information representing the thickness distribution in the surface of the steel sheet.
- a typical example is a crown, which is a thickness distribution in the width direction of a steel plate.
- the crown represents the difference between the thickness at the central portion in the width direction of the steel plate and the thickness at a position a predetermined distance (for example, 100 mm, 150 mm, etc. is used) from the end portions in the width direction of the steel plate.
- the thickness distribution information is not limited to this, and a coefficient of an approximation formula in which the thickness distribution in the width direction is approximated by a second-order or higher function may be used as the thickness distribution information.
- the thickness distribution in the longitudinal direction may be used instead of the thickness distribution in the width direction of the steel sheet.
- Such representative plate thickness and thickness distribution information correspond to data measured by a plate thickness gauge during rolling in the plate rolling process and data measured in the plate inspection process.
- the representative sheet width is the representative value for the width of the steel sheet that is the material.
- the width of the thick steel plate that is the material affects the variation in the accuracy of the outer diameter of the steel pipe that is the product.
- the width at any position in the longitudinal direction of the steel sheet can be used, or the average value of the widths in the longitudinal direction may be used.
- the steel sheet is subjected to bending and unbending deformation, so it is preferable to include attribute information representing the Bauschinger effect of the steel sheet.
- attribute information representing the Bauschinger effect a constitutive equation representing the stress-strain relationship of the steel sheet expressing the Bauschinger effect and parameter values for specifying the constitutive equation can be used. This is because these allow the mechanical properties of the steel sheet, such as kinematic hardening and isotropic hardening, to be specified, and the anisotropy of the yield stress and the like to be reflected in the finite element analysis.
- the shape formed by the molding surface 13a of the upper mold 13 and the shape formed by the pressing surface 14a of the lower mold 14 used in the C press machine can be used as operational parameters.
- the end bending width in the C press process (the width to which end bending is performed), the feed amount of the steel plate, the feed direction, and the number of feeds, the pushing force (C press force) by the hydraulic cylinder 16, and the gripping force by the clamp are operation parameters. may be used as This is because these are factors that can affect the deformation at the ends of the steel sheet in the width direction in the C-pressing process.
- the shape formed by the molding surface 13a of the upper die 13 may be given as a continuous arc having a plurality of radii of curvature, or given by an involute curve or the like.
- a parameter can be used to specify the cross-sectional shape.
- the cross-sectional shape can be specified by using the coefficients of the first and second terms of the parabola passing through the origin. It can be an operating parameter of the C press process.
- a plurality of molds are owned as the shape formed by the molding surface 13a of the upper mold 13, and they are used by appropriately replacing them.
- a mold control number for specifying the mold used in the C press process may be used as an operation parameter for the C press process.
- the operation parameters of the U-pressing process are used as inputs to the roundness prediction model M.
- FIG. As operation parameters for the U-press process, shape information of the U-press tool (information for specifying the tip shape of the U-press tool), U-press reduction amount, initial U-press support interval, and final U-press support interval can be used. can. This is because these operating parameters have a great influence on the deformation behavior of the steel sheet in the U-pressing process.
- the U-press reduction amount, the initial U-press support interval, and the final U-press support interval represent the deformation imparted to the steel sheet in both the Kaiser-type U-press apparatus and the Burson-type U-press apparatus, as described above. It is an operational parameter that can be commonly defined as a thing. However, parameters that indirectly affect these parameters may be used for each device. For example, the opening angle of the link 29 and the positional information of the sliding block 27 in the Kaiser-type U-press device may be used. This is because these are operational parameters that can be indirectly associated with any of the U-press reduction amount, the initial U-press support interval, and the final U-press support interval.
- the shape shown in FIG. 17 may be used as a U-press tool.
- the shape of the U-press tool 22 shown in FIG. 17 is such that the U-press tool 22 makes contact with the steel plate when it pushes down the steel plate.
- a shape of a side portion with a radius r smoothly connected to an arc shape with a radius R at the tip is given.
- the shape of the U press tool 22 is specified by three parameters: the angle ⁇ , the tip radius R (bottom R), and the side radius r (side r).
- the parameters for specifying the tip shape of the U-press tool in this way are called shape information of the U-press tool.
- the U-press tool management number for specifying the U-press tool to be used is specified. It may also be used as an operating parameter for the U press process.
- the operational parameters of the O press process are used as inputs to the roundness prediction model M.
- FIG. As operating parameters for the O-pressing step, the O-press reduction amount, the O-press reduction position, and the O-press die R can be used. In particular, it is preferable to use the O press reduction amount.
- the O press reduction amount When the O press reduction amount is increased, the area between the point where the restraint/pressing force is received from the upper mold and the point where it is restrained by the lower mold, mainly the 3 o'clock and 9 o'clock areas of the steel pipe. Nearby, there is no constraint by the mold, and bending and compression deformations concentrate. This will increase the curvature of that area and affect the final roundness.
- the O press reduction amount, the O press reduction position, and the O press die R are information necessary for controlling the O press device, and correspond to set values set by the host computer.
- the tube expansion rate can be used as the operation parameter of the tube expansion process.
- the roundness of the steel pipe after the pipe expansion process improves as the pipe expansion ratio increases, a value equal to or lower than the preset upper limit value is used.
- the tube expansion rate is information necessary for controlling the tube expansion device, and corresponds to a set value set by the host computer.
- the number of expansion dies and the diameter of the expansion dies may also be used as operational parameters for the expansion process.
- the roundness prediction model M generated as described above is used for online processing in the steel pipe manufacturing process to estimate the roundness of the steel pipe after the pipe expansion process. predict degree.
- an operating condition data set set as the operating condition of the steel pipe manufacturing process is obtained online (operation parameter obtaining step). This is a step of acquiring necessary data from a host computer that controls the steel pipe manufacturing process or a control computer for each forming process as an operating condition data set that is input to the roundness prediction model generated as described above. is.
- “on-line” means a series of manufacturing processes from before the start of the steel pipe manufacturing process to the completion of the pipe expansion process.
- processing does not necessarily have to be in progress in any of the forming processing steps. Even the time during which the steel sheet is waiting to be transported to the next process between each forming process is included in the "online" of the present embodiment. In addition, even before the start of the steel pipe manufacturing process and after the completion of the plate rolling process for manufacturing the steel plate to be the raw material, it can be included in the "online". This is because, when the plate rolling process for manufacturing the steel plate as the raw material is completed, it becomes possible to acquire the operating condition data set as the input of the roundness prediction model of the present embodiment.
- the input operating condition data set is supported. It is possible to predict the roundness of the steel pipe after the pipe expansion process (roundness prediction step). As a result, an open pipe is formed through a U-pressing process in which a U-shaped molded body is formed by pressing with a U-press tool, and an O-pressed process in which the seam gap of the U-shaped molded body is reduced to form an open pipe. It is possible to verify whether or not the manufacturing conditions in each step are appropriate in the steel pipe manufacturing process including the pipe expansion step of enlarging the inner diameter of the steel pipe whose ends are joined after the ends are joined. .
- the operating conditions of the U-press and O-press processes have a complex effect on the circularity of the steel pipe after the pipe expansion process. Become.
- the roundness prediction model M using the attribute information of the steel plate as the material even if there is variation in the attribute information of the steel plate in the upstream process, the influence of these factors on the roundness of the product can be quantified. can be evaluated effectively.
- the circularity of the steel pipe after the pipe expansion process is predicted using the steel pipe circularity prediction model M, and the circularity of the steel pipe is controlled as follows.
- a process to be reset is selected from among a plurality of forming processes that constitute the steel pipe manufacturing process.
- the roundness prediction model M is used to predict the roundness of the steel pipe after the pipe expansion process.
- the plurality of forming processes that constitute the steel pipe manufacturing process include a C-pressing process, a U-pressing process, an O-pressing process, and a pipe-expanding process in which plastic deformation is applied to the steel plate to process the steel pipe into a predetermined shape.
- a C-pressing process a U-pressing process
- O-pressing process a pipe-expanding process in which plastic deformation is applied to the steel plate to process the steel pipe into a predetermined shape.
- point to An arbitrary process is selected from these molding processes as the process to be reset.
- the circularity prediction model M of the steel pipe is used to predict the circularity of the steel pipe after the pipe expansion process.
- the actual data is used as the perfect circle. It can be used as an input for the degree prediction model M.
- the setting value set in advance in the host computer or the like is used as the input for the roundness prediction model M of the steel pipe. In this way, it is possible to predict the roundness of the steel pipe after the pipe expansion process for the target material.
- the roundness predicted as the roundness of the steel pipe after the pipe expansion process falls within the roundness allowed as a product.
- the operation parameter to be reset may be the operation parameter in the reset target process or the operation parameter in the molding process downstream of the reset target process.
- operation parameters for the forming process suitable for changing the roundness of the steel pipe after the tube expansion process may be selected.
- both the operation parameter in the reset target process and the operation parameter in any molding process downstream of the reset target process may be reset. This is because when there is a large difference between the predicted roundness and the roundness allowed as a product, the roundness of the steel pipe after the pipe expansion process can be effectively changed.
- Table 1 specifically shows cases of molding processes selected as reset target processes and corresponding molding processes for which operation parameters can be reset.
- the C-pressing process is selected as the process to be reset in the steel pipe manufacturing process including the C-pressing process.
- the roundness of the steel pipe after the pipe-expanding process is predicted using the setting values of the operation parameters in the forming processes including the U-pressing process and the O-pressing process. If the predicted roundness is large, it is possible to reset any operational parameters in each forming process of the C press process, U press process, O press process, and tube expansion process.
- the operating parameters to be reset may be not only the operating parameters of the C-pressing process, but also the operating parameters of other molding processes.
- case 2 and case 3 the process to be reset and the operation parameters to be reset can be selected based on the same concept as case 1.
- case 4 is a case where the tube expansion process is set as the process to be reset.
- the roundness prediction model M is used to predict the roundness of the steel pipe after the tube expansion process before starting the tube expansion process.
- the roundness prediction model M it is possible to use at least actual operation data in the U-press process and the O-press process.
- performance data of attribute information of steel sheets and operation performance data in the C press process may be used.
- the operation parameters in the tube expansion process are reset. do. It is preferable to use the expansion ratio as the operation parameter for the expansion process to be reset.
- the amount of change from the initial set value of the tube expansion rate to be reset may be reset based on actual performance data obtained from operational experience.
- the input of the roundness prediction model M includes the expansion rate of the pipe expansion process
- the re-set expansion rate value is used as the input of the roundness prediction model M, and the steel pipe after the pipe expansion process
- the suitability of the conditions to be reset may be determined by predicting the roundness.
- the example shown in FIG. 18 is a case where the O press process is selected as the process to be reset, the U press process is completed, and the U-shaped compact is transferred to the O press device.
- the operation record data in the U press process is sent to the operating condition resetting section 140 .
- the operation performance data is preferably sent via a network from a control computer provided in each molding equipment (equipment for executing the molding process).
- the information may be sent from the control computer of each forming equipment to the host computer 150 that controls the steel pipe manufacturing process, and then sent from the host computer 150 to the operating condition resetting unit 140 .
- performance data regarding the attribute information of the steel sheet is sent from the host computer 150 as necessary, and when the pretreatment process is performed, the operation performance data in the pretreatment process is used. to correct a part of the attribute information of the steel plate and send it to the operating condition resetting unit 140 .
- the width of the steel sheet used as the raw material changes in the pretreatment process
- the width of the attribute information of the steel sheet is corrected to the width after the pretreatment process.
- operation performance data in the C press process may be sent as necessary.
- the operation parameters of the reset target process and the O press process and the tube expansion process which are forming processes downstream of the reset target process, those setting values are reset from the control computer of each forming equipment.
- the setting unit 140 It is sent to the setting unit 140 .
- the operating parameter setting values for the O-pressing process and the tube expanding process are stored in the host computer 150 , they may be sent from the host computer 150 to the operating condition resetting unit 140 .
- the host computer 150 sends the operating condition resetting unit 140 a roundness target value determined according to the specifications of the steel pipe as a product.
- the operating condition resetting unit 140 uses the roundness prediction model M online to predict the roundness of the steel pipe after the pipe expansion process from this information, and calculates the predicted roundness (roundness prediction value) and Compare with the target roundness (roundness target value). Then, when the predicted roundness is smaller than the target roundness value, the operating condition resetting unit 140 does not change the set values of the operating conditions for the U-pressing process, the O-pressing process, and the pipe-expanding process. Determine the operating conditions for the rest of the forming process and manufacture the steel pipe. On the other hand, when the predicted roundness is larger than the roundness target value, the operating condition resetting unit 140 resets at least the operating conditions for the O-pressing process or the operating conditions for the tube expanding process. Specifically, the O press reduction amount in the O press step can be reset. Moreover, the tube expansion rate of the tube expansion process can be reset. Furthermore, both the O press reduction amount and the tube expansion rate can be reset.
- the operating condition resetting unit 140 again uses the reset values of the operating parameters reset in this way as the input data of the roundness prediction model M to perform roundness prediction again. It is also possible to confirm whether or not the circularity is smaller than the circularity target value, and determine the reset values of the operating conditions for the O-pressing process and the tube expanding process.
- the reset operating conditions for the O-pressing process and the tube-expanding process are sent to respective control computers, and the operating conditions for the O-pressing process and the tube-expanding process are determined.
- a steel pipe with better roundness can be manufactured. Furthermore, after executing the roundness control of the steel pipe after the pipe expansion process with the O-pressing process as the process to be reset in this way, the pipe expansion process is again performed on the steel pipe that has been formed into an open pipe and welded. Roundness control of the steel pipe after the pipe expansion process, which is the process to be reset, may be executed. This is because the accuracy of predicting the roundness of the steel pipe is further improved in a state where the operational performance data of the O-pressing process is obtained.
- the roundness is predicted in consideration of the influence of the interaction between the U-pressing process and the O-pressing process on the roundness. Since the model M is used, it is possible to set appropriate operating conditions for improving the circularity of the steel pipe after the pipe expansion process, and to manufacture a steel pipe with a high degree of circularity. In addition, it is possible to achieve highly accurate roundness control that reflects variations in the attribute information of the steel plate that is the material.
- FIG. 19 is a diagram showing the configuration of a steel pipe roundness prediction device that is an embodiment of the present invention.
- a steel pipe roundness prediction apparatus 160 according to an embodiment of the present invention includes an operation parameter acquisition unit 161, a storage unit 162, a roundness prediction unit 163, and an output unit 164. .
- the operational parameter acquisition unit 161 has an arbitrary interface that can acquire the roundness prediction model M generated by the machine learning unit, for example, from the steel pipe roundness prediction model generation device 100 .
- the operational parameter acquisition unit 161 may include a communication interface for acquiring the roundness prediction model M from the steel pipe roundness prediction model generation device 100 .
- the operational parameter acquisition unit 161 may receive the roundness prediction model M from the steel pipe roundness prediction model generation device 100 using a predetermined communication protocol.
- the operating parameter acquisition unit 161 acquires the operating conditions of the molding equipment (equipment for executing the molding process) from, for example, a control computer or a host computer provided in the equipment used in each molding process.
- the operational parameter acquisition unit 161 may include a communication interface for acquiring operational conditions. Also, the operational parameter acquisition unit 161 may acquire input information based on a user's operation.
- the steel pipe roundness prediction apparatus 160 further includes an input unit including one or more input interfaces for detecting user input and acquiring input information based on user operation. Examples of the input unit include, but are not limited to, physical keys, capacitance keys, a touch screen provided integrally with the display of the output unit, a microphone for receiving voice input, and the like.
- the input unit receives input of operating conditions for the roundness prediction model M acquired by the operation parameter acquisition unit 161 from the steel pipe roundness prediction model generating device 100 .
- the storage unit 162 includes at least one semiconductor memory, at least one magnetic memory, at least one optical memory, or a combination of at least two of these.
- the storage unit 162 functions, for example, as a main storage device, an auxiliary storage device, or a cache memory.
- the storage unit 162 stores arbitrary information used for the operation of the steel pipe roundness prediction device 160 .
- the storage unit 162 stores, for example, the roundness prediction model M acquired from the steel pipe roundness prediction model generation device 100 by the operation parameter acquisition unit 161, the operating conditions acquired from the host computer by the operation parameter acquisition unit 161, and
- the circularity information predicted by the steel pipe circularity prediction device 160 is stored.
- the storage unit 162 may store system programs, application programs, and the like.
- the roundness prediction unit 163 includes one or more processors.
- the processor is a general-purpose processor or a dedicated processor specialized for specific processing, but is not limited to these.
- the roundness prediction unit 163 is communicably connected to each component constituting the steel pipe roundness prediction device 160 and controls the overall operation of the steel pipe roundness prediction device 160 .
- the roundness prediction unit 163 can be any general-purpose electronic device such as a PC (Personal Computer) or a smart phone, for example.
- the roundness prediction unit 163 is not limited to these, and may be one or a plurality of server devices that can communicate with each other, or may be another electronic device dedicated to the roundness prediction device 160 .
- the roundness prediction unit 163 uses the operating conditions acquired via the operation parameter acquisition unit 161 and the roundness prediction model M acquired from the steel pipe roundness prediction model generation device 100 to obtain the roundness information of the steel pipe. Calculate the predicted value of
- the output unit 164 outputs the predicted value of the roundness information of the steel pipe calculated by the roundness prediction unit 163 to a device for setting the operating conditions of the forming equipment.
- the output unit 164 may include one or more output interfaces for outputting information and notifying the user.
- the output interface is, for example, a display.
- the display is, for example, an LCD or an organic EL display.
- the output unit 164 outputs data obtained by the operation of the steel pipe roundness prediction device 160 .
- the output unit 164 may be connected to the steel pipe roundness prediction device 160 as an external output device instead of being provided in the steel pipe roundness prediction device 160 .
- any method such as USB, HDMI (registered trademark), or Bluetooth (registered trademark) can be used.
- the output unit 164 may be a display that outputs information as video or a speaker that outputs information as audio, but is not limited to these.
- the output unit 164 presents the predicted value of the roundness information calculated by the roundness prediction unit 163 to the user. The user can appropriately set the operating conditions of the molding equipment based on the predicted roundness value presented by the output unit 164 .
- a more preferable form of the steel pipe roundness prediction device 160 after the pipe expansion process as described above is that the input unit 165 acquires input information based on the user's operation, and the roundness prediction unit 163 calculates the roundness It is a terminal device such as a tablet terminal having a display unit 166 that displays predicted values of information. This acquires input information based on the user's operation from the input unit 165, and updates some or all of the operation parameters of the forming process that have already been input to the steel pipe roundness prediction device 160 based on the acquired input information. It is something to do.
- the operator uses the terminal device to obtain the operation parameter acquisition unit It accepts an operation of correcting and inputting a part of the operation parameters of the molding process input to 161 .
- the operating parameter acquisition unit 161 retains the initial input data for the operating parameters of the molding process that are not corrected input from the terminal device, and changes only the operating parameters that have been corrected. do.
- the operation parameter acquisition unit 161 generates new input data for the roundness prediction model M, and the roundness prediction unit 163 calculates the prediction value of the roundness information based on the input data.
- the calculated predicted value of the roundness information is displayed on the display unit 166 of the terminal device through the output unit 164 .
- the person in charge of operation of molding equipment or the person in charge of the factory can immediately confirm the predicted value of roundness information when the operation parameter of the molding process is changed, and quickly change to the appropriate operating conditions. can be done.
- the basic data acquisition unit 110 shown in FIG. 10 set an operating condition data set including the following operating parameters.
- the target steel pipe to be the product after the pipe expansion process was API grade X56, pipe thickness 31.8 mm x outer diameter 914.4 mm.
- the attribute information of the steel sheet was set to a thickness of 31.8 mm and a width of 2751 mm, and the yield stress was included in the operating condition data set as attribute information of the steel sheet so as to correspond to a steel sheet having a tensile strength of 480 to 600 MPa.
- the width of the plate the width of the plate after the pretreatment process was set.
- the calculation conditions were set such that the curvature radius of the molding surface of the upper mold was R310 mm and the end bending was applied to the range of 180 mm from the end in the width direction as the end bending width. It was not included as an input for the circularity prediction model.
- the operating parameters of the U-press process we generated a finite element model of the U-press process corresponding to the U-press process using a Kaiser-type U-press device.
- the shape information of the U-press tool was calculated under two conditions of 178 mm and 191 mm for the width r, with a bottom R of 362 mm and a bottom R angle of ⁇ 120 degrees, and included in the operating condition data set.
- the final U press support interval was changed in the range of 564 ⁇ 30 mm, and the U press reduction amount was changed in the range of 782.6 ⁇ 12.7 mm. were included in the operating condition data set.
- the upper and lower dies were set to an O press die radius of 451 mm, the arc of the upper die was 451 mm deep, and the arc of the lower die was 438 mm deep. Also, the calculation conditions were changed so that the distance between the highest point of the upper die and the lowest point of the lower die (O press reduction amount) was 903 ⁇ 3 mm, and this was included in the operating condition data set for the O press process.
- FIG. 20 shows an example of a finite element model in the O press process.
- the tube expansion die is divided into 12 in the circumferential direction and has a shape with a radius of 390 mm, and the tube expansion rate is set in the range of 0.4 to 1.6%. and included it in the operating condition data set for the tube expansion process.
- the outer diameter shape of the steel pipe after the pipe expansion process obtained by the roundness offline calculation unit 112 is divided into 1080 points in the circumferential direction. and the difference between the maximum diameter Dmax and the minimum diameter Dmin of them was used.
- the roundness prediction model of the steel pipe after the pipe expansion process includes the final U-press support interval and the U-press reduction amount as the operating parameters of the U-press process, and the operating parameters of the O-press process. , O including the amount of press reduction. Further, the yield stress is included in the operating condition data set as the attribute information of the steel plate, and the expansion rate is included in the operating condition data set as the operating parameter of the tube expansion process. Data necessary for the finite element analysis of the forming process, including such an operating condition data set, was supplied to the circularity offline calculation unit 112 to calculate the circularity of the steel pipe after the pipe expansion process. The learning data set acquired by the calculation is stored in the database 120, and the roundness prediction model M is generated by the roundness prediction model generation unit 130.
- a two-dimensional plane strain element is set by dividing the steel plate before the C press process, which is the material, into 720 parts in the width direction and 18 parts in the thickness direction, and the C press process, U press process, A finite element analysis was performed in the order of the O press process, the welding process, and the pipe expansion process.
- the finite element analysis solver used in this example was Abaqus 2019, and the calculation time per case was approximately 3 hours.
- the number of data sets stored in the database 120 is 300, and Gaussian process regression using radial basis functions as basis functions is used as the machine learning model.
- the roundness prediction model M generated in this way is installed as an online model in the system shown in FIG. The actual value of the yield stress of the steel plate was obtained from the results of the material inspection in the plate rolling process, which is the previous process.
- the U press process is set as a process to be reset.
- the operating parameters of the U press process and the O press process were reset.
- the set value of the operating conditions for the tube expansion process was fixed at 1.0% and was not included in the reset operating parameters.
- the reset operation parameter of the U-press process is the U-press support final interval
- the reset operation parameter of the O-press process is the O-press reduction amount.
- the operation parameters after resetting were reset with a constraint that they should be within the range of the operation parameters set by the roundness offline calculation unit 112 .
- 100 steel pipes were manufactured according to the first embodiment in which such roundness control was performed.
- the roundness prediction model M was not used, the average roundness value was 7.9 mm, and the pass rate was 40%.
- the average value of circularity was 6.2 mm, and the acceptance rate was improved to 75%.
- the U press process is set as a process to be reset, and the yield stress, which is the attribute information of the steel sheet, is set after the C press process is completed and before the transition to the U press process.
- the operation parameter of the tube expansion process to be reset is the tube expansion rate, which was reset within the range of 0.6 to 1.3%.
- Other operational parameters to be reset are the same as in the first embodiment. 100 steel pipes were manufactured according to the second embodiment in which such roundness control was performed. As a result, the average roundness was 5.1 mm, and the pass rate was further improved to 90%.
- the basic data acquisition unit 110 shown in FIG. 10 set an operating condition data set including the following operating parameters.
- a steel pipe of API grade X80, pipe thickness 25.4 mm ⁇ outer diameter 558.8 mm was targeted as a product after the pipe expansion process.
- the attribute information of the steel sheet is set to a thickness of 25.0 to 27.0 mm and a width of 1662 mm. Included in operating condition data set.
- the width of the plate the width of the plate after the pretreatment process was set.
- the calculation conditions were set such that the curvature radius of the molding surface of the upper mold was R170 mm and the end bending was applied to the range of 135 mm from the end in the width direction as the end bending width. It was not included as an input for the circularity prediction model.
- the operating parameters of the U-press process we generated a finite element model of the U-press process corresponding to the U-press process using a Kaiser-type U-press device.
- the shape information of the U-press tool was calculated under conditions of a bottom R of 225 mm, a bottom R angle of ⁇ 120 degrees, and a lateral r of 110 mm, and this was included in the operating condition data set.
- the final U press support interval was changed in the range of 314 ⁇ 30 mm, and the U press reduction amount was changed in the range of 706.4 ⁇ 25.4 mm. were included in the operating condition data set.
- the upper and lower dies were set to an O press die radius R of 276 mm, the arc of the upper die was 276 mm deep, and the arc of the lower die was 264 mm deep.
- the calculation conditions were changed so that the distance between the highest point of the upper die and the lowest point of the lower die (O press reduction amount) was 578 ⁇ 3 mm, and this was included in the operating condition data set for the O press process.
- the tube expansion die is divided into 10 parts in the circumferential direction and has a shape with a radius of 240 mm, and the expansion rate is set in the range of 0.4 to 1.6%. and included it in the operating condition data set for the tube expansion process.
- the outer diameter shape of the steel pipe after the pipe expansion process obtained by the roundness offline calculation unit 112 is divided into 1080 points in the circumferential direction. and the difference between the maximum diameter Dmax and the minimum diameter Dmin of them was used.
- the roundness prediction model of the steel pipe after the pipe expansion process includes the final U-press support interval and the U-press reduction amount as the operating parameters of the U-press process, and the operating parameters of the O-press process. It includes the amount of O press reduction.
- the operating condition data set includes plate thickness and yield stress as the attribute information of the steel plate, and the operating condition data set includes the expansion rate as the operating parameter of the pipe expansion process. Data necessary for the finite element analysis of the forming process, including such an operating condition data set, was supplied to the circularity offline calculation unit 112 to calculate the circularity of the steel pipe after the pipe expansion process.
- the learning data set acquired by the calculation is stored in the database 120, and the roundness prediction model M is generated by the roundness prediction model generation unit 130.
- a two-dimensional plane strain element is set by dividing the steel plate before the C press process, which is the material, into 720 parts in the width direction and 18 parts in the thickness direction, and the C press process, U press process, A finite element analysis was performed in the order of the O press process, the welding process, and the tube expansion process.
- the finite element analysis solver used in this example was Abaqus 2019, and the calculation time per case was approximately 3 hours.
- the number of data sets stored in the database 120 is 500, and the machine learning model is an ensemble model combining a neural network and a decision tree.
- the neural network has one intermediate layer and five nodes each.
- the ReLU function was used as the activation function.
- the maximum depth of the hierarchy of the decision tree is 3, and the maximum number of leaves in the generated decision tree is 160.
- the roundness prediction model M generated in this way is installed in the system shown in FIG. 18 as an online model, and the roundness target value is set to 5 mm.
- the actual value of the yield stress of the steel plate was obtained from the results of the material inspection in the plate rolling process, which is the previous process.
- the U press process is set as a process to be reset, and after the C press process is completed and before the shift to the U press process, the actual values of the thickness and yield stress, which are the attribute information of the steel plate was used as an input for the roundness prediction model M, and the operating parameters for the U press process and the O press process were reset.
- the set value of the operating conditions for the tube expansion process was fixed at 1.0% and was not included in the reset operating parameters.
- the reset operation parameter of the U-press process is the U-press support final interval
- the reset operation parameter of the O-press process is the O-press reduction amount.
- the operation parameters after resetting were reset with a constraint that they should be within the range of the operation parameters set by the roundness offline calculation unit 112 .
- 100 steel pipes were manufactured according to the third embodiment in which such roundness control was performed.
- the roundness prediction model M was not used, the average roundness value was 5.0 mm, and the pass rate was 60%.
- the average value of circularity was 4.1 mm, and the acceptance rate was improved to 81%.
- the U-pressing process is set as a process to be reset, and after the C-pressing process is completed, before shifting to the U-pressing process, the plate thickness, which is the attribute information of the steel plate, is set.
- the actual value of the yield stress was used as an input for the roundness prediction model M, and the operation parameters of the U press process, O press process, and pipe expansion process were reset.
- the operation parameter of the tube expansion process to be reset is the tube expansion rate, which was reset within the range of 0.6 to 1.3%.
- Other operational parameters to be reset are the same as in the third embodiment. 100 steel pipes were manufactured according to the fourth embodiment in which such roundness control was performed. As a result, the average roundness was 2.6 mm, and the pass rate was further improved to 95%.
- the basic data acquisition unit 110 shown in FIG. 10 set an operating condition data set including the following operating parameters.
- a steel pipe of API grade X100, pipe thickness 12.7 mm ⁇ outer diameter 1219.2 mm was targeted as a product after the pipe expansion process.
- the attribute information of the steel sheet is set to a thickness of 12.7 to 14.3 mm and a width of 3760 mm. Included in operating condition data set.
- the width of the plate the width of the plate after the pretreatment process was set.
- the calculation conditions were set such that the curvature radius of the molding surface of the upper mold was R310 mm and the end bending was applied to the range of 180 mm from the end in the width direction as the end bending width. It was not included as an input for the circularity prediction model.
- the operating parameters of the U-press process we generated a finite element model of the U-press process corresponding to the U-press process using a Kaiser-type U-press device.
- the shape information of the U-press tool was calculated under conditions of a bottom R of 1300 mm, a bottom R angle of ⁇ 27 degrees, and a lateral r of 120 mm, and this was included in the operating condition data set.
- the U press support final interval was changed in the range of 394 ⁇ 40 mm, and the U press reduction amount was changed in the range of 858.8 ⁇ 25.4 mm. were included in the operating condition data set.
- the upper and lower dies were set to an O press die radius R of 602 mm, the arc of the upper die was 602 mm deep, and the arc of the lower die was 590 mm deep.
- the calculation conditions were changed so that the distance between the highest point of the upper die and the lowest point of the lower die (O press reduction amount) was 1200 ⁇ 5 mm, and this was included in the operating condition data set for the O press process.
- the tube expansion die is divided into 12 in the circumferential direction and has a shape with a radius of 545 mm, and the tube expansion rate is in the range of 0.5 to 1.6%. and included it in the operating condition data set for the tube expansion process.
- the outer diameter shape of the steel pipe after the pipe expansion process obtained by the roundness offline calculation unit 112 is divided into 1080 points in the circumferential direction. and the difference between the maximum diameter Dmax and the minimum diameter Dmin of them was used.
- the roundness prediction model of the steel pipe after the pipe expansion process includes the final U-press support interval and the U-press reduction amount as the operating parameters of the U-press process, and the operating parameters of the O-press process. , O including the amount of press reduction.
- the operating condition data set includes plate thickness and yield stress as the attribute information of the steel plate, and the operating condition data set includes the expansion rate as the operating parameter of the pipe expansion process. Data necessary for the finite element analysis of the forming process, including such an operating condition data set, was supplied to the circularity offline calculation unit 112 to calculate the circularity of the steel pipe after the pipe expansion process.
- the learning data set acquired by the calculation is stored in the database 120, and the roundness prediction model M is generated by the roundness prediction model generation unit 130.
- a two-dimensional plane strain element is set by dividing the steel plate before the C press process, which is the material, into 720 parts in the width direction and 18 parts in the thickness direction, and the C press process, U press process, A finite element analysis was performed in the order of the O press process, the welding process, and the tube expansion process.
- the finite element analysis solver used in this example was Abaqus 2019, and the calculation time per case was approximately 3 hours.
- the number of data sets stored in the database 120 is 400, and the gradient boosting method, which is a kind of ensemble learning using a decision tree, is used as the machine learning model.
- the number of decision trees constituting the gradient boosting decision tree was set to 10, the maximum depth of the hierarchy was set to 5, and the maximum number of leaves in the generated decision tree was set to 180.
- the roundness prediction model M generated in this way is installed as an online model in the system shown in FIG. 18, and the roundness target value is set to 10 mm.
- the actual value of the yield stress of the steel plate was obtained from the results of the material inspection in the plate rolling process, which is the previous process.
- the U-pressing process is set as a process to be reset, and after the C-pressing process is completed and before shifting to the U-pressing process, the actual values of the thickness and yield stress, which are the attribute information of the steel plate was used as an input for the roundness prediction model M, and the operating parameters for the U press process and the O press process were reset.
- the set value of the operating conditions for the tube expansion process was fixed at 1.2% and was not included in the reset operating parameters.
- the reset operation parameter of the U-press process is the U-press support final interval
- the reset operation parameter of the O-press process is the O-press reduction amount.
- the operation parameters after resetting were reset with a constraint that they should be within the range of the operation parameters set by the roundness offline calculation unit 112 .
- 100 steel pipes were manufactured according to the fifth embodiment in which such roundness control was performed.
- the roundness prediction model M was not used, the average roundness was 10.5 mm, and the pass rate was 20%.
- the average roundness was 6.3 mm, and the pass rate was improved to 69%.
- the U-pressing process is set as a process to be reset, and after the C-pressing process is completed, the plate thickness, which is the attribute information of the steel sheet, is set before shifting to the U-pressing process.
- the actual value of the yield stress was used as an input for the roundness prediction model M, and the operation parameters of the U press process, O press process, and pipe expansion process were reset.
- the operation parameter of the tube expansion process to be reset is the tube expansion rate, which was reset within the range of 0.9 to 1.5%.
- Other operational parameters to be reset are the same as in the fifth embodiment. 100 steel pipes were manufactured according to the sixth embodiment in which such roundness control was performed. As a result, the average roundness was 5.1 mm, and the pass rate was further improved to 92%.
- the basic data acquisition unit 110 shown in FIG. 10 set an operating condition data set including the following operating parameters.
- the target steel pipe to be the product after the pipe expansion process was API grade X42, pipe thickness 44.5 mm x outer diameter 1422.4 mm.
- the attribute information of the steel sheet was set to a thickness of 45.6 mm and a width of 4295 mm, and the yield stress was included in the operating condition data set as attribute information of the steel sheet so as to correspond to a steel sheet having a tensile strength of 500 MPa.
- the width of the plate the width of the plate after the pretreatment process was set.
- the calculation conditions were set such that the curvature radius of the molding surface of the upper mold was R420 mm and the end bending was applied to the range of 300 mm from the end in the width direction as the end bending width. It was not included as an input for the circularity prediction model.
- the operating parameters of the U-press process we generated a finite element model of the U-press process corresponding to the U-press process using a Kaiser-type U-press device.
- the shape information of the U-press tool calculations corresponding to multiple shape information were performed from the range of bottom R 501 to 552 mm, bottom R angle ⁇ 120 degrees, and lateral r 200 to 300 mm, and this was included in the operating condition data set.
- the final U press support interval was changed in the range of 914 ⁇ 80 mm, and the U press reduction amount was changed in the range of 858.8 ⁇ 25.4 mm. were included in the operating condition data set.
- the upper and lower dies were set to an O press die radius R of 702 mm, the arc of the upper die was 702 mm deep, and the arc of the lower die was 683 mm deep.
- the calculation conditions were changed so that the distance between the highest point of the upper die and the lowest point of the lower die (O press reduction amount) was 1415 ⁇ 5 mm, and this was included in the operating condition data set for the O press process.
- the expansion rate was set to 0.9% on the premise that the expansion die was divided into 12 in the circumferential direction and had a diameter of 620 mm.
- the outer diameter shape of the steel pipe after the pipe expansion process obtained by the roundness offline calculation unit 112 is divided into 1080 points in the circumferential direction. and the difference between the maximum diameter Dmax and the minimum diameter Dmin of them was used.
- the roundness prediction model of the steel pipe after the pipe expansion process includes the shape information of the U-press tool, the final U-press support distance, and the U-press reduction amount as the operation parameters of the U-press process.
- the operating parameters of the O press process include the O press reduction amount.
- the learning data set acquired by the calculation is stored in the database 120, and the roundness prediction model M is generated by the roundness prediction model generation unit 130.
- a two-dimensional plane strain element is set by dividing the steel plate before the C press process, which is the material, into 720 parts in the width direction and 18 parts in the thickness direction, and the C press process, U press process, A finite element analysis was performed in the order of the O press process, the welding process, and the pipe expansion process.
- the finite element analysis solver used in this example was Abaqus 2019, and the calculation time per case was approximately 3 hours.
- a roundness prediction model M was generated.
- the roundness prediction model M is a machine learning model that includes, as inputs, operating parameters for the U-press process and operating parameters for the O-press process. Gaussian process regression is used for the machine learning model, and the RBF kernel (Radial Basis Function kernel) that evaluates the similarity between variables and the White kernel (White kernel) was used.
- the circularity prediction model M generated as described above was used for online processing in the steel pipe manufacturing process to predict the circularity of the steel pipe after the pipe expansion process after the O-pressing process.
- the target is a steel pipe that meets the above manufacturing conditions.
- a reduction amount and an O press reduction amount were acquired, and an operating condition data set to be input to the roundness prediction model M was generated.
- the predicted value of the roundness of the steel pipe after the pipe expansion process is calculated and compared with the actual value of the roundness of the steel pipe after the pipe expansion process (actual roundness value). did.
- the difference between the actual roundness value and the predicted roundness value output by the roundness prediction model M was an average error of 0.3% and a standard deviation of error of 4.3%. It was confirmed that the degree prediction model M accurately predicted the roundness after the tube expansion process.
- the basic data acquisition unit 110 shown in FIG. 10 set an operating condition data set including the following operating parameters.
- the target steel pipe to be the product after the pipe expansion process was API grade X52, pipe thickness 6.4 mm x outer diameter 508.0 mm.
- the attribute information of the steel plate is set to a thickness of 6.4 to 7.4 mm and a width of 1564 mm. Included in operating condition data set.
- the width of the plate the width of the plate after the pretreatment process was set.
- a process of manufacturing a steel pipe by performing a U-pressing process, an O-pressing process, a welding process, and a pipe-expanding process on a steel plate as a material was targeted. In other words, the steel pipe was manufactured without end bending by the C press process.
- the operating parameters of the U-press process we generated a finite element model of the U-press process corresponding to the U-press process using a Kaiser-type U-press device.
- the shape information of the U-press tool was calculated under the conditions of a bottom R of 210 mm, a bottom R angle of ⁇ 120 degrees, and a lateral r of 131 mm.
- the U press support final interval is changed in the range of 154 ⁇ 30 mm
- the U press reduction amount is changed in the range of 656.6 ⁇ 25.4 mm. were included in the operating condition data set.
- the upper and lower dies were set to an O press die radius R of 251 mm, the arc of the upper die was 251 mm deep, and the arc of the lower die was 239 mm deep.
- the calculation conditions were changed so that the distance between the highest point of the upper die and the lowest point of the lower die (O press reduction amount) was 501 ⁇ 3 mm, and this was included in the operating condition data set for the O press process.
- the tube expansion die was divided into 10 sections in the circumferential direction and had a shape with a radius of 226 mm, and the tube expansion ratio was set to 1.1%.
- the roundness prediction model of the steel pipe after the pipe expansion process includes the final U-press support interval and the U-press reduction amount as the operating parameters of the U-press process, and the operating parameters of the O-press process. It includes the amount of O press reduction. Furthermore, the sheet thickness and yield stress are included in the operating condition data set as the attribute information of the steel sheet. Data necessary for the finite element analysis of the forming process, including such an operating condition data set, was supplied to the circularity offline calculation unit 112 to calculate the circularity of the steel pipe after the pipe expansion process. The learning data set acquired by the calculation is stored in the database 120, and the roundness prediction model M is generated by the roundness prediction model generation unit 130. FIG.
- two-dimensional plane strain elements are set by dividing the material steel plate into 720 parts in the width direction and 18 parts in the thickness direction.
- Finite element analysis was performed in the order of The finite element analysis solver used in this example was Abaqus 2019, and the calculation time per case was approximately 3 hours.
- a circularity prediction model M was generated when 250 pieces of data were accumulated in the database 120 .
- the roundness prediction model M is a machine learning model that includes, as inputs, steel sheet attribute information, operating parameters for the U-pressing process, and operating parameters for the O-pressing process. We used support vector regression for the machine learning model and a sigmoid kernel for the kernel function.
- the circularity prediction model M generated as described above was used for online processing in the steel pipe manufacturing process to predict the circularity of the steel pipe after the pipe expansion process after the O-pressing process.
- the target is a steel pipe that meets the above manufacturing conditions.
- a U-press reduction amount and an O-press reduction amount were acquired, and an operating condition data set to be input to the roundness prediction model M was generated. Then, as the output of the roundness prediction model M, the predicted value of the roundness of the steel pipe after the pipe expansion process is calculated and compared with the actual value of the roundness of the steel pipe after the pipe expansion process (actual roundness value). did.
- the difference between the actual roundness value and the predicted roundness value output by the roundness prediction model M was an average error of 0.2% and a standard deviation of error of 4.6%. It was confirmed that the degree prediction model M accurately predicted the roundness after the tube expansion process.
- the basic data acquisition unit 110 shown in FIG. 10 set an operating condition data set including the following operating parameters.
- the target steel pipe to be the product after the pipe expansion process was API grade X65, pipe thickness 44.5 mm x outer diameter 914.4 mm.
- the steel sheet attribute information was set to a thickness of 44.5 mm and a width of 2711 mm, and the yield stress was included in the operating condition data set as steel sheet attribute information so as to correspond to steel sheets with a tensile strength of 520 to 690 MPa.
- the width of the plate the width of the plate after the pretreatment process was set.
- the calculation conditions were set such that the curvature radius of the molding surface of the upper mold was R310 mm and the end bending was applied to the range of 195 mm from the end in the width direction as the end bending width. It was not included as an input for the circularity prediction model.
- the operating parameters of the U-press process we generated a finite element model of the U-press process corresponding to the U-press process using a Kaiser-type U-press device.
- the shape information of the U-press tool was calculated under the conditions of a bottom R of 310 mm, a bottom R angle of ⁇ 120 degrees, and a lateral r of 178 mm.
- the U press support final interval is changed in the range of 634 ⁇ 40 mm
- the U press reduction amount is changed in the range of 782.6 ⁇ 25.4 mm. were included in the operating condition data set.
- the upper and lower dies were set to an O press die radius R of 451 mm, the arc of the upper die was 451 mm deep, and the arc of the lower die was 438 mm deep.
- the calculation conditions were changed so that the distance between the highest point of the upper die and the lowest point of the lower die (O press reduction amount) was 903 ⁇ 4 mm, and this was included in the operating condition data set for the O press process.
- operation parameters for the tube expansion process it is assumed that two types of dies are used as the tube expansion dies, which are divided into 12 in the circumferential direction and have radii of 390 mm and 410 mm. 0.1% range and was included in the operating condition data set for the tube expansion process.
- the outer diameter shape of the steel pipe after the pipe expansion process obtained by the roundness offline calculation unit 112 is divided into 1080 points in the circumferential direction. and the difference between the maximum diameter Dmax and the minimum diameter Dmin of them was used.
- the roundness prediction model of the steel pipe after the pipe expansion process includes the final U-press support interval and the U-press reduction amount as the operating parameters of the U-press process, and the operating parameters of the O-press process. It includes the amount of O press reduction. Furthermore, the yield stress is included in the operating condition data set as the attribute information of the steel sheet, and the expansion die radius and expansion ratio are included in the operating condition data set as the operating parameters of the tube expansion process. Data necessary for the finite element analysis of the forming process, including such an operating condition data set, was supplied to the circularity offline calculation unit 112 to calculate the circularity of the steel pipe after the pipe expansion process. The learning data set acquired by the calculation is stored in the database 120, and the roundness prediction model M is generated by the roundness prediction model generation unit 130. FIG.
- a two-dimensional plane strain element is set by dividing the steel plate before the C press process, which is the material, into 720 parts in the width direction and 18 parts in the thickness direction, and the C press process, U press process, A finite element analysis was performed in the order of the O press process, the welding process, and the pipe expansion process.
- the finite element analysis solver used in this example was Abaqus 2019, and the calculation time per case was approximately 3 hours.
- a roundness prediction model M was generated.
- the roundness prediction model M is a machine learning model that includes, as inputs, steel sheet attribute information, operating parameters for the U-pressing process, operating parameters for the O-pressing process, and operating parameters for the tube expanding process.
- the machine learning model used a random forest with a maximum depth of 3 for the hierarchy of decision trees and a maximum number of leaves of 220 in the generated decision tree.
- the circularity prediction model M generated as described above was used for online processing in the steel pipe manufacturing process to predict the circularity of the steel pipe after the pipe expansion process after the O-pressing process.
- the target is the steel pipe that meets the above manufacturing conditions. and O press reduction were obtained.
- the tube expansion die radius and tube expansion rate which are the operating parameters of the tube expanding process, these set values were obtained from the control computer, and an operating condition data set to be input to the roundness prediction model M was generated. Then, as the output of the roundness prediction model M, the predicted value of the roundness of the steel pipe after the pipe expansion process is calculated and compared with the actual value of the roundness of the steel pipe after the pipe expansion process (actual roundness value). did.
- the difference between the actual roundness value and the predicted roundness value output by the roundness prediction model M was an average error of 0.4% and a standard deviation of error of 4.0%. It was confirmed that the degree prediction model M accurately predicted the roundness after the tube expansion process.
- the basic data acquisition unit 110 shown in FIG. 10 set an operating condition data set including the following operating parameters.
- the steel pipe to be the product after the pipe expansion process was API grade X42, pipe thickness 44.5 mm x outer diameter 609.6 mm.
- the attribute information of the steel sheet was set to a thickness of 44.5 mm and a width of 1761 mm, and the yield stress was included in the operating condition data set as the attribute information of the steel sheet so as to correspond to a steel sheet having a tensile strength of 400 to 600 MPa.
- the width of the plate the width of the plate after the pretreatment process was set.
- the radius of curvature of the molding surface of the upper mold is set to R190 mm, and the calculation conditions are set such that the end bending is applied in the range of 120 to 140 mm from the end in the width direction as the end bending width. Included in operating condition data set.
- the operating parameters of the U-press process we generated a finite element model of the U-press process corresponding to the U-press process using a Kaiser-type U-press device.
- the shape information of the U-press tool was calculated under the conditions of a bottom R of 246 mm, a bottom R angle of ⁇ 120 degrees, and a lateral r of 160 mm.
- the U press support final interval is changed in the range of 474 ⁇ 30 mm
- the U press reduction amount is changed in the range of 757.2 ⁇ 12.7 mm. were included in the operating condition data set.
- the upper and lower dies were set to an O press die radius R of 301 mm, the arc of the upper die was 301 mm deep, and the arc of the lower die was 289 mm deep.
- the calculation conditions were changed so that the distance between the highest point of the upper die and the lowest point of the lower die (O press reduction amount) was 602 ⁇ 4 mm, and this was included in the operating condition data set for the O press process.
- the tube expansion die is divided into 10 parts in the circumferential direction and has a shape with a radius of 254 mm. and included it in the operating condition data set for the tube expansion process.
- the outer diameter shape of the steel pipe after the pipe expansion process obtained by the roundness offline calculation unit 112 is divided into 1080 points in the circumferential direction. and the difference between the maximum diameter Dmax and the minimum diameter Dmin of them was used.
- the roundness prediction model of the steel pipe after the pipe expansion process includes the final U-press support interval and the U-press reduction amount as the operating parameters of the U-press process, and the operating parameters of the O-press process. It includes the amount of O press reduction.
- the yield stress is included in the operation condition data set as the attribute information of the steel plate, and the end bending width is included as the operation parameter of the C press process.
- the pipe expansion rate is included in the operational condition data set as an operational parameter of the pipe expansion process. Data necessary for the finite element analysis of the forming process, including such an operating condition data set, was supplied to the circularity offline calculation unit 112 to calculate the circularity of the steel pipe after the pipe expansion process.
- the learning data set acquired by the calculation is stored in the database 120, and the roundness prediction model M is generated by the roundness prediction model generation unit 130.
- a two-dimensional plane strain element is set by dividing the steel plate before the C press process, which is the material, into 720 parts in the width direction and 18 parts in the thickness direction, and the C press process, U press process, A finite element analysis was performed in the order of the O press process, the welding process, and the tube expansion process.
- the finite element analysis solver used in this example was Abaqus 2019, and the calculation time per case was approximately 3 hours.
- a circularity prediction model M was generated when 500 pieces of data were accumulated in the database 120 .
- the roundness prediction model M is a machine learning model that includes, as inputs, steel sheet attribute information, operating parameters for the C-pressing process, operating parameters for the U-pressing process, operating parameters for the O-pressing process, and operating parameters for the tube expanding process. Gaussian process regression with radial basis functions was used as a machine learning model.
- the circularity prediction model M generated as described above was used for online processing in the steel pipe manufacturing process to predict the circularity of the steel pipe after the pipe expansion process after the O-pressing process.
- the target is a steel pipe that meets the above manufacturing conditions.
- the final distance of the press support portion, the U-press reduction amount, and the O-press reduction amount were obtained.
- the pipe expansion rate which is an operational parameter of the pipe expansion process
- these setting values were acquired from the control computer, and an operational condition data set to be input to the roundness prediction model M was generated.
- the degree prediction model M accurately predicted the roundness after the tube expansion process.
- a method for generating a roundness prediction model for a steel pipe capable of generating a roundness prediction model for accurately predicting the roundness of a steel pipe after a pipe expansion step in a UOE steel pipe manufacturing process including a plurality of steps.
- a steel pipe roundness prediction method and a roundness prediction apparatus capable of accurately predicting the roundness of a steel pipe after a pipe expansion step in a UOE steel pipe manufacturing process including a plurality of steps. be able to.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Mechanical Engineering (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Automation & Control Theory (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Health & Medical Sciences (AREA)
Abstract
Description
まず、図1を参照して、本発明の一実施形態である鋼管の製造工程について説明する。
まず、図2,図3を参照して、Cプレス工程として、Cプレス装置を用いた鋼板の端曲げ加工を行う場合について説明する。
次に、図4~図6を参照して、Uプレス工程について説明する。
次に、図7を参照して、Oプレス工程について説明する。
次に、溶接工程について説明する。
次に、図8を参照して、拡管工程について説明する。
最後に、図9を参照して、検査工程について説明する。
次に、図10~図17を参照して、本発明の一実施形態である鋼管の真円度予測モデルの生成装置について説明する。
真円度予測モデルMの入力データとなる鋼板の属性情報としては、鋼板の降伏応力、引張強度、縦弾性係数、厚さ、板面内の厚さ分布、鋼板の厚さ方向の降伏応力の分布、バウシンガー効果の大きさ、及び表面粗さ等、拡管工程後の鋼管の真円度に影響を及ぼす任意のパラメータを用いることができる。特にUプレス工程における曲げ加工の変形状態やスプリングバックに影響を与える因子や、Oプレス工程における圧縮・曲げ加工による鋼板の変形状態やスプリングバックに影響を与える因子を指標とするとよい。
Cプレス工程の操業パラメータを真円度予測モデルMの入力に用いる場合には、Cプレス装置で使用する上金型13の成形面13aがなす形状や下金型14の押圧面14aがなす形状を特定するパラメータを操業パラメータとして用いることができる。また、Cプレス工程における端曲げ加工幅(端曲げ成形を施す幅)、鋼板の送り量、送り方向、及び送り回数、油圧シリンダ16による押し上げ力(Cプレス力)、クランプによる把持力を操業パラメータとして用いてもよい。これらは、Cプレス工程における鋼板の幅方向端部における変形に影響を与え得る因子だからである。
本実施形態では、Uプレス工程の操業パラメータを真円度予測モデルMの入力に用いる。Uプレス工程の操業パラメータとしては、Uプレス工具の形状情報(Uプレス工具の先端形状を特定するための情報)、Uプレス圧下量、Uプレス支持初期間隔、Uプレス支持最終間隔を用いることができる。これらの操業パラメータが、Uプレス工程おける鋼板の変形挙動に大きな影響を与えるからである。
本実施形態では、Oプレス工程の操業パラメータを真円度予測モデルMの入力に用いる。Oプレス工程の操業パラメータとしては、Oプレス圧下量、Oプレス圧下位置、及びOプレスダイスRを用いることができる。特にOプレス圧下量を用いることが好適である。これは、Oプレス圧下量を大きくすると、上金型より拘束・押圧力を受ける点と下金型によって拘束される点との間の領域、主に鋼管の3時方向及び9時方向の領域付近では、金型による拘束がなく、曲げ及び圧縮の変形が集中する。これにより、その領域の曲率が増加して、最終的な真円度に影響を与えるからである。このとき、Oプレス圧下量、Oプレス圧下位置、及びOプレスダイスRは、Oプレス装置を制御するために必要な情報であり、上位計算機で設定された設定値に対応する。
拡管工程の操業パラメータを真円度予測モデルMの入力に用いる場合には、拡管率を拡管工程の操業パラメータとして用いることができる。拡管率が大きいほど、拡管工程後の鋼管の真円度は向上するが、予め設定された上限値以下の値を用いる。このとき、拡管率は、拡管装置を制御するために必要な情報であり、上位計算機で設定された設定値に対応する。なお、拡管工程の操業パラメータとして、拡管率の他、拡管ダイス枚数や拡管ダイス径を用いてもよい。
次に、本発明の一実施形態である鋼管の真円度予測方法について説明する。
次に、図18を参照して、本発明の一実施形態である鋼管の真円度制御方法について説明する。
次に、図19を参照して、本発明の一実施形態である鋼管の真円度予測装置について説明する。
本実施例では、図10に示す基礎データ取得部110において、以下の操業パラメータを含む操業条件データセットを設定した。拡管工程後の製品となる鋼管は、APIグレードX56、管厚31.8mm×外径914.4mmを対象とした。まず、鋼板の属性情報は板厚31.8mm、板幅2751mmに設定し、引張強度480~600MPaの鋼板に対応するように、降伏応力を鋼板の属性情報として操業条件データセットに含めた。なお、板幅については前処理工程後の板幅を設定した。Cプレス工程の操業パラメータについては、上金型の成形面の曲率半径をR310mmとして、端曲げ加工幅として幅方向端部から180mmの範囲に端曲げ加工を付与する計算条件を設定したが、真円度予測モデルの入力には含めなかった。
本実施例では、図10に示す基礎データ取得部110において、以下の操業パラメータを含む操業条件データセットを設定した。拡管工程後の製品となる鋼管は、APIグレードX80、管厚25.4mm×外径558.8mmを対象とした。まず、鋼板の属性情報は板厚25.0~27.0mm、板幅1662mmに設定し、引張強度600~780MPaの鋼板に対応するように、鋼板の板厚と降伏応力を鋼板の属性情報として操業条件データセットに含めた。なお、板幅については前処理工程後の板幅を設定した。Cプレス工程の操業パラメータについては、上金型の成形面の曲率半径をR170mmとして、端曲げ加工幅として幅方向端部から135mmの範囲に端曲げ加工を付与する計算条件を設定したが、真円度予測モデルの入力には含めなかった。
本実施例では、図10に示す基礎データ取得部110において、以下の操業パラメータを含む操業条件データセットを設定した。拡管工程後の製品となる鋼管は、APIグレードX100、管厚12.7mm×外径1219.2mmを対象とした。まず、鋼板の属性情報は板厚12.7~14.3mm、板幅3760mmに設定し、引張強度720~900MPaの鋼板に対応するように、鋼板の板厚と降伏応力を鋼板の属性情報として操業条件データセットに含めた。なお、板幅については前処理工程後の板幅を設定した。Cプレス工程の操業パラメータについては、上金型の成形面の曲率半径をR310mmとして、端曲げ加工幅として幅方向端部から180mmの範囲に端曲げ加工を付与する計算条件を設定したが、真円度予測モデルの入力には含めなかった。
本実施例では、図10に示す基礎データ取得部110において、以下の操業パラメータを含む操業条件データセットを設定した。拡管工程後の製品となる鋼管は、APIグレードX42、管厚44.5mm×外径1422.4mmを対象とした。まず、鋼板の属性情報は板厚45.6mm、板幅4295mmに設定し、引張強度500MPaの鋼板に対応するように、降伏応力を鋼板の属性情報として操業条件データセットに含めた。なお、板幅については前処理工程後の板幅を設定した。Cプレス工程の操業パラメータについては、上金型の成形面の曲率半径をR420mmとして、端曲げ加工幅として幅方向端部から300mmの範囲に端曲げ加工を付与する計算条件を設定したが、真円度予測モデルの入力には含めなかった。
本実施例では、図10に示す基礎データ取得部110において、以下の操業パラメータを含む操業条件データセットを設定した。拡管工程後の製品となる鋼管は、APIグレードX52、管厚6.4mm×外径508.0mmを対象とした。まず、鋼板の属性情報は板厚6.4~7.4mm、板幅1564mmに設定し、引張強度440~640MPaの鋼板に対応するように、鋼板の板厚と降伏応力を鋼板の属性情報として操業条件データセットに含めた。なお、板幅については前処理工程後の板幅を設定した。本実施例では、素材となる鋼板に対して、Uプレス工程、Oプレス工程、溶接工程、及び拡管工程を行って、鋼管を製造する工程を対象とした。つまり、Cプレス工程による端曲げ加工を行うことなく鋼管を製造した。
本実施例では、図10に示す基礎データ取得部110において、以下の操業パラメータを含む操業条件データセットを設定した。拡管工程後の製品となる鋼管は、APIグレードX65、管厚44.5mm×外径914.4mmを対象とした。まず、鋼板の属性情報は板厚44.5mm、板幅2711mmに設定し、引張強度520~690MPaの鋼板に対応するように、降伏応力を鋼板の属性情報として操業条件データセットに含めた。なお、板幅については前処理工程後の板幅を設定した。Cプレス工程の操業パラメータについては、上金型の成形面の曲率半径をR310mmとして、端曲げ加工幅として幅方向端部から195mmの範囲に端曲げ加工を付与する計算条件を設定したが、真円度予測モデルの入力には含めなかった。
本実施例では、図10に示す基礎データ取得部110において、以下の操業パラメータを含む操業条件データセットを設定した。拡管工程後の製品となる鋼管は、APIグレードX42、管厚44.5mm×外径609.6mmを対象とした。まず、鋼板の属性情報は板厚44.5mm、板幅1761mmに設定し、引張強度400~600MPaの鋼板に対応するように、降伏応力を鋼板の属性情報として操業条件データセットに含めた。なお、板幅については前処理工程後の板幅を設定した。Cプレス工程の操業パラメータについては、上金型の成形面の曲率半径をR190mmとして、端曲げ加工幅として幅方向端部から120~140mmの範囲に端曲げ加工を付与する計算条件を設定して操業条件データセットに含めた。
11 搬送機構
12A,12B プレス機構
13 上金型
13a 成形面
14 下金型
14a 押圧面
15 ツールホルダ
16 油圧シリンダ
17 クランプ機構
20 機枠
21 昇降シリンダ
22,37 Uプレス工具(Uパンチ)
23 吊下げ部材
24 下部床面
25 ロッド
26 摺動シリンダ
27 摺動ブロック
28 サドル(受台)
29 リンク
30 回動中心
31 アーム
32 ブレーキロール
33 サドル部
34 U曲げ支え部
35 下型(ロッカーダイ)
36 回転支点
38 クッション
40 下ダイス
41 上ダイス
51 拡管ダイス
52 テーパー外周面
53 プルロッド
60 アーム
61a,61b 変位計
62 回転角度検出器
63 回転アーム
64a,64b 押圧ローラ
100 鋼管の真円度予測モデルの生成装置
110 基礎データ取得部
111 操業条件データセット
112 真円度オフライン計算部
112a~112c 有限要素モデル生成部
112d 有限要素解析ソルバー
120 データベース
130 真円度予測モデル生成部
140 操業条件再設定部
150 上位計算機
160 鋼管の真円度予測装置
161 操業パラメータ取得部
162 記憶部
163 真円度予測部
164 出力部
165 入力部
166 表示部
P 鋼管
S 鋼板
Claims (12)
- Uプレス工具により鋼板をU字状断面の成形体に成形加工するUプレス工程、前記U字状断面の成形体をオープン管に成形加工するOプレス工程、及び前記オープン管の幅方向端部同士を接合した鋼管に対して拡管による成形加工を行う拡管工程を含む鋼管の製造工程における、前記拡管工程後の鋼管の真円度を予測する鋼管の真円度予測モデルの生成方法であって、
前記Uプレス工程の操業パラメータの中から選択した1つ以上の操業パラメータ、及び前記Oプレス工程の操業パラメータの中から選択した1つ以上の操業パラメータを含む操業条件データセットを入力データとして含み、前記拡管工程後の鋼管の真円度情報を出力データとする数値計算を、前記操業条件データセットを変更しながら複数回実行することにより、前記操業条件データセットと対応する前記拡管工程後の鋼管の真円度情報のデータの組を学習用データとして複数生成する基礎データ取得ステップと、
前記基礎データ取得ステップにおいて生成された複数の学習用データを用いて、前記操業条件データセットを入力データ、拡管工程後の鋼管の真円度情報を出力データとする真円度予測モデルを機械学習により生成する真円度予測モデル生成ステップと、
を含む、鋼管の真円度予測モデルの生成方法。 - 前記基礎データ取得ステップは、有限要素法を利用して前記操業条件データセットから前記拡管工程後の鋼管の真円度情報を算出するステップを含む、請求項1に記載の鋼管の真円度予測モデルの生成方法。
- 前記真円度予測モデルは、前記操業条件データセットとして、前記鋼板の属性情報の中から選択した1つ以上のパラメータを含む、請求項1又は2に記載の鋼管の真円度予測モデルの生成方法。
- 前記真円度予測モデルは、前記操業条件データセットとして、前記拡管工程の操業パラメータの中から選択した1つ以上の操業パラメータを含む、請求項1~3のうち、いずれか1項に記載の鋼管の真円度予測モデルの生成方法。
- 前記鋼管の製造工程は、前記Uプレス工程に先立って前記鋼板の幅方向端部の端曲げにより成形加工するCプレス工程を含み、前記真円度予測モデルは、前記操業条件データセットとして、前記Cプレス工程の操業パラメータの中から選択した1つ以上の操業パラメータを含む、請求項1~4のうち、いずれか1項に記載の鋼管の真円度予測モデルの生成方法。
- 前記Uプレス工程の操業パラメータは、前記Uプレス工具の形状情報、Uプレス圧下量、Uプレス支持初期間隔、及びUプレス支持最終間隔のうちの1つ以上の操業パラメータを含む、請求項1~5のうち、いずれか1項に記載の鋼管の真円度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、ガウシアン過程回帰、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1~6のうち、いずれか1項に記載の鋼管の真円度予測モデルの生成方法。
- 請求項1~7のうち、いずれか1項に記載の鋼管の真円度予測モデルの生成方法により生成された鋼管の真円度予測モデルの入力として、前記鋼管の製造工程の操業条件として設定される操業条件データセットをオンラインで取得する操業パラメータ取得ステップと、
前記真円度予測モデルに、前記操業パラメータ取得ステップにおいて取得した前記操業条件データセットを入力し、拡管工程後の鋼管の真円度情報を予測する真円度予測ステップと、
を含む、鋼管の真円度予測方法。 - 請求項8に記載の鋼管の真円度予測方法を用いて、前記鋼管の製造工程を構成する複数の成形加工工程の中から選択した再設定対象工程の開始前に、前記拡管工程後の鋼管の真円度情報を予測し、予測された鋼管の真円度情報に基づいて、少なくとも前記再設定対象工程の操業パラメータの中から選択した1つ以上の操業パラメータ、又は前記再設定対象工程よりも下流側の成形加工工程の操業パラメータの中から選択した1つ以上の操業パラメータを再設定するステップを含む、鋼管の真円度制御方法。
- 請求項9に記載の鋼管の真円度制御方法を用いて鋼管を製造するステップを含む、鋼管の製造方法。
- Uプレス工具により鋼板をU字状断面の成形体に加工するUプレス工程、前記U字状断面の成形体をオープン管に加工するOプレス工程、前記オープン管の幅方向端部同士を接合した鋼管に対して拡管による成形加工を行う拡管工程を含む鋼管の製造工程における、前記拡管工程後の鋼管の真円度を予測する鋼管の真円度予測装置であって、
前記Uプレス工程の操業パラメータの中から選択した1つ以上の操業パラメータ、及び前記Oプレス工程の操業パラメータの中から選択した1つ以上の操業パラメータを含む操業条件データセットを入力データとして含み、前記拡管工程後の鋼管の真円度情報を出力データとする数値計算を、前記操業条件データセットを変更しながら複数回実行することにより、前記操業条件データセットと対応する前記拡管工程後の鋼管の真円度情報のデータの組を学習用データとして複数生成する基礎データ取得部と、
前記基礎データ取得部において生成された複数の学習用データを用いて、前記操業条件データセットを入力データ、拡管工程後の鋼管の真円度情報を出力データとする真円度予測モデルを機械学習により生成する真円度予測モデル生成部と、
前記鋼管の製造工程の操業条件として設定される操業条件データセットをオンラインで取得する操業パラメータ取得部と、
前記真円度予測モデル生成部において生成された真円度予測モデルを用いて、前記操業パラメータ取得部により取得した前記操業条件データセットに対応する拡管工程後の鋼管の真円度情報をオンラインで予測する真円度予測部と、
を備える、鋼管の真円度予測装置。 - ユーザの操作に基づく入力情報を取得する入力部と、前記真円度情報を表示する表示部と、を有する端末装置を備え、
前記操業パラメータ取得部は、前記入力部が取得した入力情報に基づいて、前記鋼管の製造工程における操業条件データセットの一部又は全部を更新し、
前記表示部は、前記更新された操業条件データセットを用いて前記真円度予測部が予測した前記鋼管の真円度情報を表示する、請求項11に記載の鋼管の真円度予測装置。
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2022534400A JP7264314B2 (ja) | 2021-04-05 | 2022-03-15 | 鋼管の真円度予測モデルの生成方法、真円度予測方法、真円度制御方法、製造方法、及び真円度予測装置 |
CN202280021837.7A CN117015446A (zh) | 2021-04-05 | 2022-03-15 | 钢管的制造方法、钢管的真圆度预测方法、控制方法、预测模型生成方法及预测装置 |
EP22784443.8A EP4272883A4 (en) | 2021-04-05 | 2022-03-15 | METHOD FOR PRODUCING A STEEL PIPE ROUNDNESS PREDICTION MODEL, ROUNDNESS PREDICTION METHOD, ROUNDNESS CONTROL METHOD, MANUFACTURING METHOD AND ROUNDNESS PREDICTION DEVICE |
BR112023020131A BR112023020131A2 (pt) | 2021-04-05 | 2022-03-15 | Método de geração de modelo de previsão de perda de circularidade de tubos de aço, método de previsão de perda de circularidade de tubos de aço, método de controle de perda de circularidade de tubos de aço, método de fabricação de tubos de aço e dispositivo de previsão de perda de circularidade de tubos de aço |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2021063903 | 2021-04-05 | ||
JP2021-063903 | 2021-04-05 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022215458A1 true WO2022215458A1 (ja) | 2022-10-13 |
Family
ID=83546196
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2022/011604 WO2022215458A1 (ja) | 2021-04-05 | 2022-03-15 | 鋼管の真円度予測モデルの生成方法、真円度予測方法、真円度制御方法、製造方法、及び真円度予測装置 |
Country Status (5)
Country | Link |
---|---|
EP (1) | EP4272883A4 (ja) |
JP (1) | JP7264314B2 (ja) |
CN (1) | CN117015446A (ja) |
BR (1) | BR112023020131A2 (ja) |
WO (1) | WO2022215458A1 (ja) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS5550916A (en) | 1978-10-07 | 1980-04-14 | Sumitomo Metal Ind Ltd | Forming method for straight seam welded large diameter pipe |
JPH0471737A (ja) | 1990-07-10 | 1992-03-06 | Sumitomo Metal Ind Ltd | 大径管の製造方法 |
JP2002346629A (ja) * | 2001-05-30 | 2002-12-03 | Nippon Steel Corp | バースト特性に優れた高強度鋼管の製造方法 |
JP2004141936A (ja) | 2002-10-25 | 2004-05-20 | Jfe Steel Kk | Uoe鋼管の製造方法 |
JP2012137813A (ja) * | 2010-12-24 | 2012-07-19 | Nippon Steel Corp | 品質予測装置、品質予測方法、プログラムおよびコンピュータ読み取り可能な記録媒体 |
JP6519896B1 (ja) * | 2018-03-15 | 2019-05-29 | オムロン株式会社 | 学習装置、学習方法、及びそのプログラム |
WO2022009575A1 (ja) * | 2020-07-10 | 2022-01-13 | Jfeスチール株式会社 | 鋼管の真円度予測モデルの生成方法、鋼管の真円度予測方法、鋼管の真円度制御方法、鋼管の製造方法、及び鋼管の真円度予測装置 |
WO2022009576A1 (ja) * | 2020-07-10 | 2022-01-13 | Jfeスチール株式会社 | 鋼管の真円度予測方法、鋼管の真円度制御方法、鋼管の製造方法、鋼管の真円度予測モデルの生成方法、及び鋼管の真円度予測装置 |
-
2022
- 2022-03-15 JP JP2022534400A patent/JP7264314B2/ja active Active
- 2022-03-15 CN CN202280021837.7A patent/CN117015446A/zh active Pending
- 2022-03-15 BR BR112023020131A patent/BR112023020131A2/pt unknown
- 2022-03-15 EP EP22784443.8A patent/EP4272883A4/en active Pending
- 2022-03-15 WO PCT/JP2022/011604 patent/WO2022215458A1/ja active Application Filing
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS5550916A (en) | 1978-10-07 | 1980-04-14 | Sumitomo Metal Ind Ltd | Forming method for straight seam welded large diameter pipe |
JPH0471737A (ja) | 1990-07-10 | 1992-03-06 | Sumitomo Metal Ind Ltd | 大径管の製造方法 |
JP2002346629A (ja) * | 2001-05-30 | 2002-12-03 | Nippon Steel Corp | バースト特性に優れた高強度鋼管の製造方法 |
JP2004141936A (ja) | 2002-10-25 | 2004-05-20 | Jfe Steel Kk | Uoe鋼管の製造方法 |
JP2012137813A (ja) * | 2010-12-24 | 2012-07-19 | Nippon Steel Corp | 品質予測装置、品質予測方法、プログラムおよびコンピュータ読み取り可能な記録媒体 |
JP6519896B1 (ja) * | 2018-03-15 | 2019-05-29 | オムロン株式会社 | 学習装置、学習方法、及びそのプログラム |
WO2022009575A1 (ja) * | 2020-07-10 | 2022-01-13 | Jfeスチール株式会社 | 鋼管の真円度予測モデルの生成方法、鋼管の真円度予測方法、鋼管の真円度制御方法、鋼管の製造方法、及び鋼管の真円度予測装置 |
WO2022009576A1 (ja) * | 2020-07-10 | 2022-01-13 | Jfeスチール株式会社 | 鋼管の真円度予測方法、鋼管の真円度制御方法、鋼管の製造方法、鋼管の真円度予測モデルの生成方法、及び鋼管の真円度予測装置 |
Non-Patent Citations (1)
Title |
---|
KOICHIRO NISHIKAWA: "IMPROVEMENT OF SIZE AND GAGE CONTROL IN STEEL PIPE.", TETSU TO HAGANE: JOURNAL OF THE IRON AND STEEL INSTITUTE OF JAPAN, IRON AND STEEL INSTITUTE OF JAPAN. TOKYO., JP, vol. 79., no. 03., 1 January 1993 (1993-01-01), JP , pages 250 - 262., XP000367843, ISSN: 0021-1575 * |
Also Published As
Publication number | Publication date |
---|---|
EP4272883A4 (en) | 2024-07-03 |
BR112023020131A2 (pt) | 2023-11-14 |
JPWO2022215458A1 (ja) | 2022-10-13 |
JP7264314B2 (ja) | 2023-04-25 |
CN117015446A (zh) | 2023-11-07 |
EP4272883A1 (en) | 2023-11-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2022009576A1 (ja) | 鋼管の真円度予測方法、鋼管の真円度制御方法、鋼管の製造方法、鋼管の真円度予測モデルの生成方法、及び鋼管の真円度予測装置 | |
WO2022009575A1 (ja) | 鋼管の真円度予測モデルの生成方法、鋼管の真円度予測方法、鋼管の真円度制御方法、鋼管の製造方法、及び鋼管の真円度予測装置 | |
Shinkin et al. | E ngineering calculations for processes involved in the production of large-diameter pipes by the sms meer technology | |
Wong et al. | Effects of roller path and geometry on the flow forming of solid cylindrical components | |
KR20160124848A (ko) | 벤딩 프레스 성형용 금형 | |
JP6958775B1 (ja) | 鋼管の真円度予測方法、鋼管の真円度制御方法、鋼管の製造方法、鋼管の真円度予測モデルの生成方法、及び鋼管の真円度予測装置 | |
JP6958776B1 (ja) | 鋼管の真円度予測モデルの生成方法、鋼管の真円度予測方法、鋼管の真円度制御方法、鋼管の製造方法、及び鋼管の真円度予測装置 | |
Li et al. | Cross wedge rolling failure mechanisms and industrial application | |
Dang et al. | Incremental bending of three-dimensional free form metal plates using minimum energy principle and model-less control | |
JP7264314B2 (ja) | 鋼管の真円度予測モデルの生成方法、真円度予測方法、真円度制御方法、製造方法、及び真円度予測装置 | |
CN105246609A (zh) | 钢管的冲压成形方法及钢管的制造方法 | |
WO2022215459A1 (ja) | 鋼管の真円度予測方法、真円度制御方法、製造方法、真円度予測モデルの生成方法、及び真円度予測装置 | |
Shim et al. | Multi-stage forming using optimized preform in the line array roll set process and its industrial application | |
JP7168047B1 (ja) | 鋼管の真円度予測モデルの生成方法、鋼管の真円度予測方法、鋼管の真円度制御方法、鋼管の製造方法、及び鋼管の真円度予測装置 | |
RU2817631C2 (ru) | Способ прогнозирования овальности стальной трубы, способ регулирования овальности стальной трубы, способ изготовления стальной трубы, способ генерирования модели прогнозирования овальности стальной трубы и устройство для прогнозирования овальности стальной трубы | |
Azizoğlu et al. | Finite Element Analysis of cold pilgering using elastic roll dies | |
RU2817714C2 (ru) | Способ генерирования модели прогнозирования овальности стальной трубы, способ прогнозирования овальности стальной трубы, способ регулирования овальности стальной трубы, способ изготовления стальной трубы и устройство для прогнозирования овальности стальной трубы | |
WO2023007925A1 (ja) | 鋼管の真円度予測方法、鋼管の真円度制御方法、鋼管の製造方法、鋼管の真円度予測モデルの生成方法、及び鋼管の真円度予測装置 | |
RU2804572C1 (ru) | Способ генерирования модели прогнозирования овальности стальной трубы, способ прогнозирования овальности стальной трубы, способ регулирования овальности стальной трубы, способ изготовления стальной трубы и устройство для прогнозирования овальности стальной трубы | |
Wang et al. | Research on multi-roll roll forming process of thick plate | |
RU2799579C1 (ru) | Сособ прогнозирования овальности стальной трубы, способ регулирования овальности стальной трубы, способ изготовления стальной трубы, способ генерирования модели прогнозирования овальности стальной трубы и устройство для прогнозирования овальности стальной трубы | |
Fan et al. | Multi-objective optimization of crimping of large-diameter welding pipe | |
RU2660464C1 (ru) | Способ производства сварных прямошовных труб большого диаметра для магистральных трубопроводов | |
Azizoğlu et al. | Finite element modeling of tube deformation during cold pilgering | |
CN112859735B (zh) | Jco成型管形在线闭环控制方法、系统、装置 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
ENP | Entry into the national phase |
Ref document number: 2022534400 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: 22784443 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2022784443 Country of ref document: EP Effective date: 20230804 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 202280021837.7 Country of ref document: CN |
|
WWE | Wipo information: entry into national phase |
Ref document number: P6002547/2023 Country of ref document: AE |
|
REG | Reference to national code |
Ref country code: BR Ref legal event code: B01A Ref document number: 112023020131 Country of ref document: BR |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2023127934 Country of ref document: RU |
|
ENP | Entry into the national phase |
Ref document number: 112023020131 Country of ref document: BR Kind code of ref document: A2 Effective date: 20231002 |