CN117015448A - Press line, press forming condition calculation method, and press forming condition calculation program - Google Patents
Press line, press forming condition calculation method, and press forming condition calculation program Download PDFInfo
- Publication number
- CN117015448A CN117015448A CN202280018559.XA CN202280018559A CN117015448A CN 117015448 A CN117015448 A CN 117015448A CN 202280018559 A CN202280018559 A CN 202280018559A CN 117015448 A CN117015448 A CN 117015448A
- Authority
- CN
- China
- Prior art keywords
- press
- metal material
- forming
- press forming
- occurrence
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004364 calculation method Methods 0.000 title description 32
- 239000007769 metal material Substances 0.000 claims abstract description 407
- 239000000463 material Substances 0.000 claims abstract description 146
- 238000010801 machine learning Methods 0.000 claims abstract description 85
- 238000004519 manufacturing process Methods 0.000 claims abstract description 81
- 230000007547 defect Effects 0.000 claims abstract description 42
- 230000002093 peripheral effect Effects 0.000 claims abstract description 31
- 238000000034 method Methods 0.000 claims description 86
- 238000010008 shearing Methods 0.000 claims description 80
- 230000037303 wrinkles Effects 0.000 claims description 70
- 238000005520 cutting process Methods 0.000 claims description 43
- 238000004080 punching Methods 0.000 claims description 35
- 230000008569 process Effects 0.000 claims description 20
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000005259 measurement Methods 0.000 claims 4
- 239000002184 metal Substances 0.000 claims 2
- 230000002401 inhibitory effect Effects 0.000 abstract 1
- 238000003825 pressing Methods 0.000 description 25
- 238000000465 moulding Methods 0.000 description 15
- 238000004458 analytical method Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 12
- 230000000295 complement effect Effects 0.000 description 10
- 238000013473 artificial intelligence Methods 0.000 description 8
- 230000008859 change Effects 0.000 description 7
- 238000010438 heat treatment Methods 0.000 description 7
- 238000010191 image analysis Methods 0.000 description 6
- 230000007246 mechanism Effects 0.000 description 6
- 229910000831 Steel Inorganic materials 0.000 description 5
- 239000011248 coating agent Substances 0.000 description 5
- 238000000576 coating method Methods 0.000 description 5
- 238000007619 statistical method Methods 0.000 description 5
- 239000010959 steel Substances 0.000 description 5
- 238000005452 bending Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 238000006073 displacement reaction Methods 0.000 description 4
- 238000009826 distribution Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 125000006850 spacer group Chemical group 0.000 description 4
- 238000005336 cracking Methods 0.000 description 3
- 239000003921 oil Substances 0.000 description 3
- 238000005096 rolling process Methods 0.000 description 3
- 229910001335 Galvanized steel Inorganic materials 0.000 description 2
- 150000001875 compounds Chemical class 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 230000002950 deficient Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000008397 galvanized steel Substances 0.000 description 2
- 230000020169 heat generation Effects 0.000 description 2
- 230000010365 information processing Effects 0.000 description 2
- 239000010687 lubricating oil Substances 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000005507 spraying Methods 0.000 description 2
- -1 TiC or CrN Chemical class 0.000 description 1
- 229910000797 Ultra-high-strength steel Inorganic materials 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000000227 grinding Methods 0.000 description 1
- 238000005338 heat storage Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000001678 irradiating effect Effects 0.000 description 1
- 238000005461 lubrication Methods 0.000 description 1
- 238000009966 trimming Methods 0.000 description 1
- 238000011144 upstream manufacturing Methods 0.000 description 1
Landscapes
- Shaping Metal By Deep-Drawing, Or The Like (AREA)
Abstract
The press line of the present invention includes: a first press machine that shears an outer peripheral portion of a metal material using a blanking die; a second press machine that forms a press-formed part by press-forming the metal material sheared by the first press machine using a forming die; a pretreatment device provided downstream of the first press machine and configured to perform a predetermined pretreatment on the metal material; a measuring unit that measures information related to a material characteristic value of a metal material before press forming; and a control device for inputting the material characteristic value and the manufacturing information of the metal material, and inputting the material characteristic value and the manufacturing information of the metal material to be formed measured by the measuring unit to a machine learning model which takes the material characteristic value and the manufacturing information of the metal material to be formed as input and takes the press forming condition of the metal material to be formed as output, thereby calculating the press forming condition for inhibiting the generation of the forming defect for the metal material to be formed, and performing feedforward control on at least one of the second press machine and the pretreatment device according to the calculated press forming condition.
Description
Technical Field
The present invention relates to a press line for manufacturing press-formed parts, a press-forming condition calculation method, and a press-forming condition calculation program.
Background
In general, a body member of an automobile is manufactured by press forming at low cost and with high productivity. The press forming is performed by pressing a material such as a steel sheet with a die provided in a press machine. In actual mass production press molding of a vehicle body component, materials, mold shapes, construction methods, press molding conditions, and the like have been confirmed in advance by CAE (Computer Aided Engineering: computer aided engineering) technology and component trial production so that molding defects such as cracks, wrinkles, surface strain, and dimensional accuracy defects do not occur. However, it is very difficult to always produce the same quality vehicle body parts in mass production press forming. For example, although the mechanical properties of a steel sheet are within the standards established by automobile manufacturers, there are cases where the properties such as tensile strength and stretchability vary within the standard range depending on the components of the steel sheet, the rolling conditions, the heat treatment temperature and other manufacturing conditions. In particular, in ultra-high strength steel sheets with a wide range of applications in recent years, the range of variation in characteristics tends to be large.
On the other hand, in the case of a mold, abrasion of the mold surface and peeling of the coating film occur as the number of times of use in mass production press forming increases from the state of a new product manufactured by the mold manufacturer. In addition, in the case of using a galvanized steel sheet or the like as a material, galvanized steel on the surface of the material peels off and adheres to the mold, and thus sliding characteristics between the mold and the material such as a friction coefficient gradually change. When the processing heat of the material during press forming is transferred to the die, the die steel stores heat and expands thermally. Therefore, the press forming conditions vary with a slight variation in the shape of the die. The cause of such fluctuation in the quality of the vehicle body member is an example, and in mass production press forming, there are a plurality of fluctuation factors in the material, the die, and the press forming conditions. Therefore, if the production conditions adversely affecting the production overlap, poor molding occurs sporadically.
In view of such a background, patent document 1 and patent document 2 propose methods for suppressing occurrence of forming defects in mass production press forming. Specifically, patent document 1 describes a method of controlling press forming conditions based on a characteristic value of a material subjected to press forming and a state quantity during press forming. Patent document 2 describes a method of controlling press forming conditions based on a difference between a part shape after press forming and a standard part shape.
Patent document 1: japanese patent No. 5000694
Patent document 2: international publication No. 2020/111061
However, the method described in patent document 1 does not consider information on the molding result as to whether or not molding failure occurs in the member manufactured under the controlled press molding conditions. Therefore, even if the characteristic value and the state quantity used for control fall within the standard value, there is a possibility that the mass production stability cannot be ensured when the molding failure occurs due to the characteristic value and the state quantity not used for control. On the other hand, since the control object in the method described in patent document 2 is only the initial position of the movable die, there is no means for ensuring the dimensional accuracy of the molded part in press molding using a press machine without a movable die. Further, since it is necessary to obtain a correlation between the shape of the molded part and the initial position of the movable mold in advance for each movable mold, a lot of labor and cost are required.
Disclosure of Invention
The present invention has been made in view of the above problems, and an object of the present invention is to provide a press line that can suppress occurrence of forming failure without requiring much labor and cost. Another object of the present invention is to provide a press forming condition calculation method and a press forming condition calculation program capable of calculating press forming conditions that suppress occurrence of forming failure. Another object of the present invention is to provide a press line that can suppress the occurrence of cracks in a metal material without requiring much labor and cost. Another object of the present invention is to provide a press forming condition calculation method and a press forming condition calculation program capable of calculating press forming conditions that suppress occurrence of cracks in a metal material. Another object of the present invention is to provide a press line that can suppress the occurrence of wrinkles in a metal material without requiring much labor and cost. Another object of the present invention is to provide a press forming condition calculation method and a press forming condition calculation program capable of calculating press forming conditions that suppress occurrence of wrinkles in a metal material. Another object of the present invention is to provide a press line that can suppress occurrence of dimensional accuracy failure of press-formed members without requiring much labor and cost. Another object of the present invention is to provide a press-forming condition calculation method and a press-forming condition calculation program capable of calculating press-forming conditions that suppress occurrence of dimensional accuracy failure in a press-formed member. Another object of the present invention is to provide a press line that can suppress occurrence of die damage and surface quality failure of press-formed members due to die damage without requiring much labor and cost. Another object of the present invention is to provide a press-forming condition calculation method and a press-forming condition calculation program capable of calculating press-forming conditions that suppress occurrence of die damage and surface quality defects of a press-formed member associated with the die damage.
A press line according to claim 1 of the present invention includes: a first press machine that shears an outer peripheral portion of a metal material using a blanking die; a second press machine for forming a press-formed part by press-forming the metal material sheared by the first press machine using a forming die; a pretreatment device provided downstream of the first press machine and configured to perform a predetermined pretreatment on the metal material; a measuring unit that measures information on a material characteristic value of the metal material before press forming; and a control device that calculates press forming conditions for suppressing occurrence of forming failure for the metal material to be formed by inputting the material characteristic value and the manufacturing information of the metal material to be formed measured by the measuring means into a machine learning model that is input with the material characteristic value and the manufacturing information of the metal material to be formed and output with press forming conditions for suppressing occurrence of forming failure for the metal material to be formed, and performs feed-forward control for at least one of the second press machine and the pretreatment device based on the calculated press forming conditions.
A press line according to claim 2 of the present invention includes: a first press machine that shears an outer peripheral portion of a metal material using a blanking die; a second press machine for forming a press-formed part by press-forming the metal material sheared by the first press machine using a forming die; a pretreatment device provided downstream of the first press machine and configured to perform a predetermined pretreatment on the metal material; a measuring unit that measures information related to the metal material during or after press forming; and a control device that calculates press forming conditions for suppressing occurrence of forming failure for a subsequent metal material by inputting information on the metal material during press forming or after press forming into a machine learning model that is inputted with information on the metal material during press forming or after press forming and is outputted with press forming conditions for suppressing occurrence of forming failure for the metal material, and feedback-controls at least one of the second press machine and the pretreatment device based on the calculated press forming conditions.
A press line according to claim 3 of the present invention includes: a first press machine that shears an outer peripheral portion of a metal material using a blanking die; a second press machine for forming a press-formed part by press-forming the metal material sheared by the first press machine using a forming die; a pretreatment device provided downstream of the first press machine and configured to perform a predetermined pretreatment on the metal material; a measuring unit that measures a residual magnetic field of the metal material before shearing by the first press machine and/or a shearing load of the metal material during shearing by the first press machine; and a control device that calculates a press forming condition for suppressing occurrence of a crack for a metal material to be formed by inputting a residual magnetic field of the metal material before cutting by the first press and/or a shear load of the metal material and manufacturing information of the metal material during cutting by the first press, and inputting a residual magnetic field of the metal material before cutting by the first press and/or a shear load of the metal material during cutting by the first press and manufacturing information of the metal material, which are measured by the measuring means, by using a machine learning model that outputs press forming conditions of the metal material for suppressing occurrence of a crack of the metal material, and performs feedforward control for at least one of the second press and the pretreatment device based on the calculated press forming condition.
A press line according to claim 4 of the present invention includes: a first press machine that shears an outer peripheral portion of a metal material using a blanking die; a second press machine for forming a press-formed part by press-forming the metal material sheared by the first press machine using a forming die; a pretreatment device provided downstream of the first press machine and configured to perform a predetermined pretreatment on the metal material; a measuring unit that measures information related to the metal material during or after press forming; and a control device that calculates a press forming condition for suppressing occurrence of cracks for a subsequent metal material by inputting information on the metal material during press forming or after press forming, to a machine learning model that is input with information on the metal material during press forming or after press forming and that is output with a press forming condition for suppressing occurrence of cracks for the metal material, and that performs feedback control for at least one of the second press machine and the pretreatment device based on the calculated press forming condition.
A press line according to claim 5 of the present invention includes: a first press machine that shears an outer peripheral portion of a metal material using a blanking die; a second press machine for forming a press-formed part by press-forming the metal material sheared by the first press machine using a forming die; a pretreatment device provided downstream of the first press machine and configured to perform a predetermined pretreatment on the metal material; a measuring unit that measures a residual magnetic field of the metal material before shearing by the first press machine and/or a shearing load of the metal material during shearing by the first press machine; and a control device that calculates press forming conditions for suppressing occurrence of wrinkles of the metal material for the metal material to be formed by inputting a residual magnetic field of the metal material before the cutting by the first press and/or a cutting load of the metal material and manufacturing information of the metal material during the cutting by the first press, and inputting a residual magnetic field of the metal material before the cutting by the first press and/or a cutting load of the metal material during the cutting by the first press and/or manufacturing information of the metal material, which are measured by the measuring means, into a machine learning model that outputs press forming conditions of the metal material for suppressing occurrence of wrinkles of the metal material, and performs feedforward control for at least one of the second press and the pretreatment device based on the calculated press forming conditions.
A press line according to claim 6 of the present invention includes: a first press machine that shears an outer peripheral portion of a metal material using a blanking die; a second press machine for forming a press-formed part by press-forming the metal material sheared by the first press machine using a forming die; a pretreatment device provided downstream of the first press machine and configured to perform a predetermined pretreatment on the metal material; a measuring unit that measures information related to the metal material during or after press forming; and a control device that calculates press forming conditions for suppressing occurrence of wrinkles for a subsequent metal material by inputting information on the metal material during press forming or after press forming into a machine learning model that is input with information on the metal material during press forming or after press forming and that is output with press forming conditions for suppressing occurrence of wrinkles of the metal material, and that feedback-controls at least one of the second press machine and the pretreatment device based on the calculated press forming conditions.
A press line according to claim 7 of the present invention includes: a first press machine that shears an outer peripheral portion of a metal material using a blanking die; a second press machine for forming a press-formed part by press-forming the metal material sheared by the first press machine using a forming die; a pretreatment device provided downstream of the first press machine and configured to perform a predetermined pretreatment on the metal material; a measuring unit that measures at least one of a residual magnetic field of the metal material before shearing by the first press, a shearing load of the metal material during shearing by the first press, a shape of the metal material before shearing by the second press, and a placement position of the metal material with respect to the forming die; and a control device for inputting at least one of a shape of the metal material before shearing by the first punch, a shearing load of the metal material before shearing by the first punch, a position of the metal material relative to the forming die, and manufacturing information of the metal material, and for calculating a press forming condition of the metal material for which occurrence of dimensional failure of the press-formed part is suppressed, using a machine learning model in which the press forming condition of the metal material is output, the machine learning model being inputted with at least one of a shape of the metal material before shearing by the first punch, a shape of the metal material before shearing by the second punch, and manufacturing information of the metal material, and for which occurrence of dimensional failure of the press-formed part is suppressed, the press forming condition being calculated, and for which occurrence of dimensional failure of the press-formed part is suppressed, the press forming condition being feedforward by the press-forming device being calculated based on at least one of the first punch forming condition and the second press forming condition being calculated.
A press line according to claim 8 of the present invention includes: a first press machine that shears an outer peripheral portion of a metal material using a blanking die; a second press machine for forming a press-formed part by press-forming the metal material sheared by the first press machine using a forming die; a pretreatment device provided downstream of the first press machine and configured to perform a predetermined pretreatment on the metal material; a measuring unit that measures information on a shape of the press-formed member; and a control device that calculates press forming conditions for suppressing occurrence of dimensional accuracy failure of the press-formed member for a subsequent metal material by inputting information on the shape of the press-formed member measured by the measuring means to a machine learning model that is input with information on the shape of the press-formed member and that is output with press forming conditions for suppressing occurrence of dimensional accuracy failure of the press-formed member, and that feedback-controls at least one of the second press and the pretreatment device based on the calculated press forming conditions.
A press line according to claim 9 of the present invention includes: a first press machine that shears an outer peripheral portion of a metal material using a blanking die; a second press machine for forming a press-formed part by press-forming the metal material sheared by the first press machine using a forming die; a pretreatment device provided downstream of the first press machine and configured to perform a predetermined pretreatment on the metal material; a measuring unit that measures information related to the metal material during or after press forming; and a control device for calculating, for a subsequent metal material, a press forming condition for suppressing occurrence of die damage and surface quality failure of a press-formed member due to die damage by inputting information on the metal material during or after press forming measured by the measuring means to a machine learning model having the information on the metal material during or after press forming as an input and having the press forming condition for suppressing occurrence of die damage and surface quality failure of a press-formed member due to die damage as an output, and performing feedback control for at least one of the second press and the pretreatment device based on the calculated press forming condition.
The press forming condition calculation method according to claim 1 of the present invention includes the steps of: the press forming conditions for suppressing the occurrence of forming failure are calculated for the metal material to be formed by inputting the material characteristic value and the manufacturing information of the metal material to be formed into a machine learning model which is inputted with the material characteristic value and the manufacturing information of the metal material and which is outputted with the press forming conditions for suppressing the occurrence of forming failure of the metal material to be formed.
The press forming condition calculation method according to claim 2 of the present invention includes the steps of: the press forming conditions for suppressing the occurrence of forming defects are calculated for a metal material to be formed by inputting information on the metal material during or after press forming and inputting information on the metal material during or after press forming into a machine learning model which is inputted with information on the press forming conditions for suppressing the occurrence of forming defects and outputting the press forming conditions for the metal material.
The press forming condition calculation method according to claim 3 of the present invention includes the steps of: the method includes the step of calculating a press forming condition for suppressing occurrence of a crack for a metal material to be formed by inputting a residual magnetic field of the metal material before cutting by a punch for cutting an outer peripheral portion of the metal material and/or a cutting load of the metal material and manufacturing information of the metal material during cutting by the punch, and by inputting a machine learning model for outputting a press forming condition for suppressing occurrence of a crack of the metal material by using the metal material as an output.
The press forming condition calculation method according to claim 4 of the present invention includes the steps of: the method includes the steps of inputting information related to a metal material during or after press forming, and inputting information related to the metal material during or after press forming into a machine learning model which is output by taking press forming conditions of the metal material for suppressing occurrence of cracks in the metal material, thereby calculating press forming conditions for suppressing occurrence of cracks in a subsequent metal material.
The press forming condition calculation method according to claim 5 of the present invention includes the steps of: the press forming conditions for suppressing the occurrence of wrinkles in the metal material to be formed are calculated by inputting a machine learning model which takes as input a residual magnetic field of the metal material before shearing by a press machine for shearing an outer peripheral portion of the metal material using a punching die and/or a shearing load of the metal material and manufacturing information of the metal material during shearing by the press machine and takes as output press forming conditions of the metal material for suppressing the occurrence of wrinkles in the metal material.
The press forming condition calculation method according to claim 6 of the present invention includes the steps of: the press forming conditions for suppressing the occurrence of wrinkles in the subsequent metal material are calculated by inputting information on the metal material during or after press forming into a machine learning model which is inputted with information on the metal material during or after press forming and outputted with the press forming conditions for suppressing the occurrence of wrinkles in the metal material.
The press forming condition calculation method according to claim 7 of the present invention includes the steps of: the method includes the steps of calculating, for a machine learning model in which a residual magnetic field of the metal material before shearing by a first punch that shears an outer peripheral portion of the metal material using a punching die, a shearing load of the metal material during shearing by the first punch, a shape of the metal material before shearing by a second punch that forms a press-formed part by press-forming the metal material sheared by the first punch using a forming die, and manufacturing information of the metal material and at least one of a position where the metal material is arranged with respect to the forming die are input, and manufacturing information of the metal material is output, and in which a press-forming condition of the metal material in which occurrence of dimensional accuracy failure of the press-formed part is suppressed is output, a residual magnetic field of the metal material before shearing by the first punch, a shearing load of the metal material during shearing by the first punch, a shape of the metal material before shearing by the second punch, and manufacturing information of the metal material with respect to at least one of the forming die are input, thereby suppressing occurrence of dimensional accuracy of the press-formed metal material.
The press forming condition calculation method according to claim 8 of the present invention includes the steps of: the press-forming conditions for suppressing occurrence of dimensional accuracy failure of the press-formed member are calculated for the subsequent metal material by inputting information on the shape of the press-formed member after press-forming into a machine learning model which is inputted with information on the shape of the press-formed member formed by press-forming the metal material using a forming die and which is outputted with press-forming conditions of the metal material for suppressing occurrence of dimensional accuracy failure of the press-formed member.
The press forming condition calculation method according to claim 9 of the present invention includes the steps of: the method includes the steps of inputting information related to a metal material during or after press forming, and inputting information related to the metal material during or after press forming into a machine learning model which is output by taking as a press forming condition for suppressing occurrence of die damage and surface quality defects of the press formed member associated with the die damage, thereby calculating press forming conditions for suppressing occurrence of die damage and surface quality defects of the press formed member associated with the die damage for a subsequent metal material.
A press forming condition calculation program according to claim 1 of the present invention causes a computer to execute: the press forming conditions for suppressing the occurrence of forming failure are calculated for the metal material to be formed by inputting the material characteristic value and the manufacturing information of the metal material to be formed into a machine learning model which is inputted with the material characteristic value and the manufacturing information of the metal material and which is outputted with the press forming conditions for suppressing the occurrence of forming failure of the metal material to be formed.
A press forming condition calculation program according to claim 2 of the present invention causes a computer to execute: the press forming conditions for suppressing the occurrence of forming defects are calculated for a metal material to be formed by inputting information on the metal material during or after press forming and inputting information on the metal material during or after press forming into a machine learning model which is inputted with information on the press forming conditions for suppressing the occurrence of forming defects and outputting the press forming conditions for the metal material.
A press forming condition calculation program according to claim 3 of the present invention causes a computer to execute: the method includes the step of calculating a press forming condition for suppressing occurrence of a crack for a metal material to be formed by inputting a residual magnetic field of the metal material before cutting by a punch for cutting an outer peripheral portion of the metal material and/or a cutting load of the metal material and manufacturing information of the metal material during cutting by the punch, and by inputting a machine learning model for outputting a press forming condition for suppressing occurrence of a crack of the metal material by using the metal material as an output.
A press forming condition calculation program according to claim 4 of the present invention causes a computer to execute: the method includes the steps of inputting information related to a metal material during or after press forming, and inputting information related to the metal material during or after press forming into a machine learning model which is output by taking press forming conditions of the metal material for suppressing occurrence of cracks in the metal material, thereby calculating press forming conditions for suppressing occurrence of cracks in a subsequent metal material.
A press forming condition calculation program according to claim 5 of the present invention causes a computer to execute: the press forming conditions for suppressing the occurrence of wrinkles in the metal material to be formed are calculated by inputting a machine learning model which takes as input a residual magnetic field of the metal material before shearing by a press machine for shearing an outer peripheral portion of the metal material using a punching die and/or a shearing load of the metal material and manufacturing information of the metal material during shearing by the press machine and takes as output press forming conditions of the metal material for suppressing the occurrence of wrinkles in the metal material.
A press forming condition calculation program according to claim 6 of the present invention causes a computer to execute: the press forming conditions for suppressing the occurrence of wrinkles in the subsequent metal material are calculated by inputting information on the metal material during or after press forming into a machine learning model which is inputted with information on the metal material during or after press forming and outputted with the press forming conditions for suppressing the occurrence of wrinkles in the metal material.
A press forming condition calculation program according to claim 7 of the present invention causes a computer to execute: the method includes the steps of calculating, for a machine learning model in which a residual magnetic field of the metal material before shearing by a first punch that shears an outer peripheral portion of the metal material using a punching die, a shearing load of the metal material during shearing by the first punch, a shape of the metal material before shearing by a second punch that forms a press-formed part by press-forming the metal material sheared by the first punch using a forming die, and manufacturing information of the metal material and at least one of a position where the metal material is arranged with respect to the forming die are input, and manufacturing information of the metal material is output, and in which a press-forming condition of the metal material in which occurrence of dimensional accuracy failure of the press-formed part is suppressed is output, a residual magnetic field of the metal material before shearing by the first punch, a shearing load of the metal material during shearing by the first punch, a shape of the metal material before shearing by the second punch, and manufacturing information of the metal material with respect to at least one of the forming die are input, thereby suppressing occurrence of dimensional accuracy of the press-formed metal material.
A press forming condition program according to claim 8 of the present invention causes a computer to execute: the press-forming conditions for suppressing occurrence of dimensional accuracy failure of the press-formed member are calculated for the subsequent metal material by inputting information on the shape of the press-formed member after press-forming into a machine learning model which is inputted with information on the shape of the press-formed member formed by press-forming the metal material using a forming die and which is outputted with press-forming conditions of the metal material for suppressing occurrence of dimensional accuracy failure of the press-formed member.
A press forming condition calculation program according to claim 9 of the present invention causes a computer to execute: the method includes the steps of inputting information related to a metal material during or after press forming, and inputting information related to the metal material during or after press forming into a machine learning model which is output by taking as a press forming condition for suppressing occurrence of die damage and surface quality defects of the press formed member associated with the die damage, thereby calculating press forming conditions for suppressing occurrence of die damage and surface quality defects of the press formed member associated with the die damage for a subsequent metal material.
According to the press line of the present invention, the occurrence of molding failure can be suppressed without requiring much labor and cost. According to the press forming condition calculation method and the press forming condition calculation program of the present invention, press forming conditions that suppress occurrence of forming failure can be calculated. According to the press line of the present invention, the occurrence of cracks in the metal material can be suppressed without requiring much labor and cost. According to the press forming condition calculation method and the press forming condition calculation program of the present invention, it is possible to calculate press forming conditions that suppress occurrence of cracks in a metal material. According to the press line of the present invention, the occurrence of wrinkles in the metal material can be suppressed without requiring much labor and cost. According to the press forming condition calculation method and the press forming condition calculation program of the present invention, press forming conditions that suppress occurrence of wrinkles in the metal material can be calculated. According to the press line of the present invention, the occurrence of defective dimensional accuracy of the press-formed member can be suppressed without requiring much labor and cost. According to the press-forming condition calculation method and the press-forming condition calculation program of the present invention, it is possible to calculate press-forming conditions that suppress occurrence of dimensional accuracy failure in a press-formed member. According to the press line of the present invention, the occurrence of die damage and surface quality failure of the press-formed member due to the die damage can be suppressed without requiring much labor and cost. According to the press-forming condition calculation method and the press-forming condition calculation program of the present invention, it is possible to calculate press-forming conditions that suppress occurrence of die damage and surface quality failure of a press-formed member associated with the die damage.
Drawings
Fig. 1 is a schematic view showing a structure of a general press line.
Fig. 2 is a schematic diagram showing a structure of a modification of the press line shown in fig. 1.
Fig. 3 is a schematic diagram showing the structure of a press line according to embodiment 1 of the present invention.
Fig. 4 is a schematic diagram showing a structure of a modification of the press line shown in fig. 3.
Fig. 5 is a schematic diagram showing the structure of a press line according to embodiment 2 of the present invention.
Fig. 6 is a schematic diagram showing a structure of a modification of the press line shown in fig. 5.
Fig. 7 is a schematic diagram showing the structure of a press line according to embodiment 3 of the present invention.
Fig. 8 is a schematic diagram showing a structure of a modification of the press line shown in fig. 7.
Fig. 9 is a block diagram showing the configuration of a control device according to embodiments 1 to 5 of the present invention.
Detailed Description
Hereinafter, the structure of a press line according to embodiments 1 to 3 of the present invention will be described with reference to the drawings.
[ Structure of usual stamping line ]
First, a structure of a general press line will be described with reference to fig. 1 and 2.
Fig. 1 is a schematic view showing a structure of a general press line. As shown in fig. 1, in a general press line 100, a coil-shaped metal material (hereinafter, referred to as coil) C shipped from a material manufacturer is first mounted on an uncoiler 2 disposed at the front end of the press line 100. Next, the coil C is unwound by the unwind straightener 3 or the like and then inserted into the press line 100. Next, a blanking process is performed to cut out the outer periphery of the press-formed member from the coil material C according to the shape of the target press-formed member. The punching step is performed by a press machine provided with a punching die 4, and the punching die 4 has an upper die composed of an upper blade and a pressing plate, and a lower die composed of a lower blade.
Next, the coil material C is conveyed by a conveyor belt, a robot arm, a feeder, or other conveyance device 5 to a mechanical press 7 having a forming die 6 composed of an upper die and a lower die, and a press forming step of forming the coil material C into a target shape by drawing and bending is performed. In general, the press forming process of a body member of an automobile is composed of about 1 to 5 steps, and includes a trimming step of cutting off surplus material, a punching step of punching, and other shearing steps in addition to press forming. The press-formed part P after all the steps are inspected, and if there is no problem in quality, it is conveyed to an assembly line for the product.
The press line 100 is generally a tandem press line in which the coil C is transported between the individual mechanical presses 7 by the transport device 5, or a multi-station press line in which a plurality of dies are provided in one mechanical press 7 and the coil C is transported between the dies by a feeder device in the mechanical press 7. As another form of the press line 100, as shown in fig. 2, there are cases where the coil material C shipped from the material manufacturer is punched out once in a coil material processing center or the like, and the coil material C is delivered as a plate material to a factory or the like where press forming is performed.
In a typical press line 100 as shown in fig. 1 and 2, when forming defects (cracks, wrinkles, surface strain, dimensional accuracy defects, and the like of a coil C), die damage, and surface quality defects of press-formed members due to the die damage occur during mass production press forming, mass production press forming is temporarily stopped, and the cause is examined. As a countermeasure, the coil material C is changed to another batch material or a material of another material manufacturer, and the die is subjected to correction such as partial cutting or grinding, and correction of press forming conditions of the mechanical press 7. Therefore, a large amount of labor and cost are required until the mass production press forming is resumed, and countermeasures are required. Therefore, the press line according to embodiments 1 to 3 of the present invention does not require much labor and cost by the following configuration, and suppresses the occurrence of forming failure, die damage, and surface quality failure of press-formed members due to die damage. Hereinafter, the structure of the press line according to embodiments 1 to 3 of the present invention will be described with reference to fig. 3 to 9.
[ embodiment 1 ]
Fig. 3 is a schematic diagram showing the structure of a press line according to embodiment 1 of the present invention. As shown in fig. 3, unlike the normal press line 100 shown in fig. 1, the press line 1 according to embodiment 1 of the present invention includes one or more sensors 11 on the upstream side of the servo press 8 (or the servo die cushion) that performs the press forming step. Specifically, the sensor 11 is provided in the press or the punching die 4 that performs the punching process before the punching process. The sensor 11 is constituted by, for example, a shape measuring device, a thermometer, a load cell, a magnetic field measuring device, etc., and measures information on material characteristic values of the coil material C before press forming, such as yield strength, tensile strength, stretchability, n value, r value, porosity, hardness, temperature, shape, etc.
The press line 1 according to embodiment 1 of the present invention includes a control device 12. The details of the control device 12 will be described later, but the control device 12 is provided with a machine learning model that takes as input a material property value and manufacturing information of the coil material C and takes as output a press forming condition of the coil material C that suppresses occurrence of forming failure, die damage, and surface quality failure of a press formed member accompanying the die damage. The control device 12 inputs the material property value and the manufacturing information of the coil material C to be formed measured by the sensor 11 into the machine learning model, thereby calculating press forming conditions for suppressing occurrence of forming failure, die damage, and surface quality failure of the press-formed member associated with the die damage for the coil material C to be formed. Examples of the press forming conditions to be calculated include forming load, forming operation, and wrinkle pressing force. The control device 12 performs feed-forward control of at least one of the servo press 8 and the pretreatment device 14 provided downstream of the punching process based on the calculated press forming conditions. The forming die 6 of the servo press 8 is provided with a movable die mechanism, a cam mechanism, a distance block with a height and a standby position that can be changed, and other means capable of changing press forming conditions. Examples of the pretreatment device 14 include a device for spraying lubricating oil onto the coil C, a heating device for heating the coil C, and the like.
The information on the production of the coil C includes information on the composition of the coil C, heat treatment conditions, rolling conditions, and the like. The manufacturing information of the web C is supplied from the material manufacturing factory 13 side, and is associated with an identifier such as an IC chip, a QR code (registered trademark), or a bar code given to the web C. The control device 12 reads the identifier by the reading device every time the roll C is replaced, thereby acquiring the manufacturing information of the roll C.
As shown in fig. 4, in the case of the press line 1 different from the press forming factory, the sensor 11 is provided in the press machine or the punching die 4 that performs punching before the punching step. In this case, the information measured by the sensor 11 is input to a control device 12a provided on the side of a factory (coil processing center) for punching the coil C, and then is transmitted to a control device 12b provided on the side of the factory for press forming via an electric communication line such as the internet, for example, by a transmitting device 15 and a receiving device 16.
[ embodiment 2 ]
Fig. 5 is a schematic diagram showing the structure of a press line according to embodiment 2 of the present invention. As shown in fig. 5, unlike the normal press line 100 shown in fig. 1, the press line 1 according to embodiment 2 of the present invention includes one or more sensors 11 on the downstream side of the servo press 8 (or the servo die cushion) that performs the press forming step. Specifically, the sensor 11 is provided in the forming die 6, the servo press 8, the conveying device 5, and the inspection step. The sensor 11 is constituted by a microphone, acoustic emission (Acoustic Emission), a camera, a thermometer, a load meter, a laser light receiving meter, a displacement meter, a shape measuring device, and the like, and measures information on the coil C during or after press forming, such as sound, vibration, a product image, temperature, load, light, and shape.
The press line 1 according to embodiment 2 of the present invention includes a control device 12. The details of the control device 12 will be described later, but the control device 12 is provided with a machine learning model that takes as input information on the coil material C during or after press forming and takes as output press forming conditions of the coil material C that suppress occurrence of forming failure, die damage, and surface quality failure of the press-formed member accompanying the die damage. The control device 12 inputs information on the coil material C during or after press forming measured by the sensor 11 into a machine learning model, and then calculates press forming conditions for suppressing occurrence of forming failure, die damage, and surface quality failure of the press-formed member due to the die damage for the press-formed coil material C. Examples of the press forming conditions to be calculated include forming load, forming operation, and wrinkle pressing force. The control device 12 performs feedback control on at least one of the servo press 8 and the preprocessing device 14 provided downstream of the punching process, based on the calculated press forming conditions. The forming die 6 of the servo press 8 is provided with a movable die mechanism, a cam mechanism, a distance block with a height and a standby position that can be changed, and other means capable of changing press forming conditions. Examples of the pretreatment device 14 include a device for spraying lubricating oil onto the coil C, a heating device for heating the coil C, and the like.
The information on the production of the coil C includes information on the composition of the coil C, heat treatment conditions, rolling conditions, and the like. The manufacturing information of the web C is associated with an identifier such as an IC chip, a QR code (registered trademark), or a bar code given to the web C. The control device 12 reads the identifier by the reading device every time the roll C is replaced, thereby acquiring the manufacturing information of the roll C. As shown in fig. 6, in the same manner as in the case of the press line 1 different from the press forming factory, in which the coil C is punched, one or more sensors 11 are provided downstream of the servo press 8 in the press forming step, and feedback control by the control device 12 is performed.
[ embodiment 3 ]
Fig. 7 is a schematic diagram showing a structure of a press line according to embodiment 3 of the present invention. As shown in fig. 7, the press line 1 according to embodiment 3 of the present invention is configured by a combination of the press line 1 according to embodiment 1 of the present invention shown in fig. 3 and the press line 1 according to embodiment 2 of the present invention shown in fig. 5. In addition, in the same manner as in the case where the factory for punching out the coil material C is different from the factory for press forming, as shown in fig. 8, the press line 1 shown in fig. 4 can be combined with the press line 1 shown in fig. 6 to form the press line 1.
[ Structure of control device ]
Next, the configuration of the control device 12 according to embodiment 1 to embodiment 5 in the press line 1 will be described. The functions of the control device 12 described later are realized by executing a program by the internal arithmetic device 122. The program may be provided by recording a file in a form that can be installed or executed on a computer-readable recording medium such as a CD-ROM, a floppy disk, or a CD-R, DVD. The program may be stored in a computer connected to a network such as an electric communication line such as the internet, a telephone communication network such as a mobile phone, or a wireless communication network such as WiFi (registered trademark), and may be downloaded and provided via a network.
[ embodiment 1 ]
Fig. 9 is a block diagram showing the configuration of a control device according to embodiments 1 to 5 of the present invention. As shown in fig. 9, the control device 12 according to embodiment 1 of the present invention is configured by an information processing device such as a computer or a workstation, and includes a database 121 and an arithmetic device 122.
The database 121 is configured by a nonvolatile memory device, and stores the material characteristic value of the coil material C before press forming, information on the coil material C during press forming or after press forming, and manufacturing information (hereinafter, referred to as input information) of the coil material C measured by the sensor 11.
The arithmetic unit 122 is constituted by a CPU or the like in the information processing apparatus, and controls the operation of the entire control apparatus 12. In the present embodiment, the computing device 122 uses the material property values and press forming conditions of the coil material C stored in the database 121 as input values, and performs operations such as theoretical analysis by CAE technology and FEM (finite element method), thereby qualitatively or quantitatively predicting press forming results such as the presence or absence, degree, and the like of occurrence of forming defects corresponding to the input values. However, since the prediction accuracy of the poor forming of FEM is not reliable based on the current theoretical analysis, an error occurs between the predicted value and the actual value of the press forming result.
Therefore, the arithmetic device 122 obtains the directionality of the press forming condition for suppressing the occurrence of the forming failure based on the prediction result of the press forming result. The computing device 122 compensates for the error in the predicted value of the press forming result based on the analysis result of the actual result value of the mass-produced press forming, thereby correcting the press forming condition in the direction in which the occurrence of the forming failure is suppressed. As the complement method, a method of experimentally obtaining in advance a complement coefficient calculated by an error between a prediction result and an actual result value based on the CAE technique, a method via a machine learning model aiming at minimizing the error, and the like can be exemplified. The arithmetic device 122 stores data of press forming results corresponding to the material characteristics of the coil material C and the corrected press forming conditions in the database 121.
The arithmetic device 122 performs statistical analysis using data such as the material property value of the coil C, the press forming condition, and the actual press forming result, analyzes the relationship between the material property value of the coil C, the press forming condition, and the press forming result, and stores the analysis result in the database 121. The computing device 122 generates a machine learning model that takes the input information as described above as input and takes press forming conditions that suppress occurrence of forming failure as output by a method such as artificial intelligence or machine learning using data stored in the database 121. The computing device 122 inputs the input information into the machine learning model according to a calculation instruction of the press forming condition for suppressing occurrence of the forming failure, thereby calculating the press forming condition for suppressing occurrence of the forming failure corresponding to the input information, and controls the press line 1 according to the calculated press forming condition.
[ embodiment 2 ]
In embodiment 2, the arithmetic device 122 obtains the directionality of the press forming condition for suppressing the occurrence of the crack in the coil C based on the prediction result of the press forming result. The computing device 122 compensates for the error in the predicted value of the press forming result based on the analysis result of the actual result value of the mass production press, thereby suppressing the press forming condition in the direction in which the occurrence of the crack in the coil C is suppressed. As the complement method, a method of experimentally obtaining in advance a complement coefficient calculated by an error between a prediction result and an actual result value based on the CAE technique, a method via a machine learning model aiming at minimizing the error, and the like can be exemplified. The arithmetic device 122 stores data of press forming results corresponding to the material characteristics of the coil material C and the corrected press forming conditions in the database 121.
The arithmetic device 122 performs statistical analysis using data such as the material property value of the coil C, the press forming condition, and the actual press forming result, analyzes the relationship between the material property value of the coil C, the press forming condition, and the press forming result, and stores the analysis result in the database 121. The computing device 122 generates a machine learning model that takes the input information as described above as input and takes press forming conditions for suppressing occurrence of cracks in the coil C as output by a method such as artificial intelligence or machine learning using data stored in the database 121. The computing device 122 inputs the input information into the machine learning model according to a calculation instruction of the press forming condition for suppressing the occurrence of the crack of the coil C, thereby calculating the press forming condition for suppressing the occurrence of the crack of the coil C corresponding to the input information. Examples of the press forming conditions to be calculated include forming load, forming operation, and wrinkle pressing force. The control device 12 performs feedback control on at least one of the servo press 8 and the preprocessing device 14 provided downstream of the punching process, based on the calculated press forming conditions.
Further, the material property values of the coil C are greatly affected by, in particular, the stretchability, the hole expansion ratio, the n value, and the r value, with respect to the occurrence of cracks in the coil C. Therefore, the control device 12 calculates appropriate press forming conditions by measuring and analyzing the fluctuation of the material characteristic values before press forming, and suppresses the occurrence of cracking of the coil material C by feed-forward control. In the present embodiment, the control device 12 estimates the ductility-related material property values such as the stretchability, the hole expansibility, the n-value, and the r-value by correlating the measured values of the material strength (yield strength (YS), and the Tensile Strength (TS)) measured on line with the manufacturing information of the coil material C by using an artificial intelligence method, a machine learning method, or the like. The information on the material strength at this time can be measured by measuring the shear load at the time of punching the coil material C or measuring the residual magnetic field after applying a pulse magnetic field to the coil material C before punching, as shown in table 1 below.
On the other hand, if a crack occurs in the coil C, the measured values such as sound, vibration, image, temperature, load, laser leakage area, and die strain change during or after press forming. Therefore, in the present embodiment, the control device 12 calculates appropriate press forming conditions by measuring the fluctuation of the measured value, predicting and analyzing the trend of the measured value, and suppresses the occurrence of cracking in the coil C by feedback control. As shown in table 1 below, sounds, vibrations, and the like during press forming can be measured by a microphone and Acoustic Emission (AE). If a crack occurs in the coil C, a crack sound and vibration of the press machine and the die associated with the occurrence of the crack occur, and therefore, the presence or absence of the occurrence of the crack in the coil C can be detected.
In addition to directly detecting cracks by imaging the press-formed member with a camera and performing image analysis, the change in inflow amount of the material can be detected by performing image analysis on the contour of the edge of the material after the drawing forming. The lower the inflow amount of the material is, the higher the risk of crack generation is, and therefore, the sign of crack generation can also be detected. Further, when the temperature of the press-molded member during or after press molding is measured by a thermal imager or the like, the temperature distribution in the press-molded member can be measured. When the material is deformed by press forming, the material generates heat during processing, and therefore the greater the deformation of the material, that is, the higher the risk of cracking, the higher the temperature. Therefore, not only the crack of the press-formed member but also the state immediately before the crack such as the neck can be detected.
On the other hand, the heat storage amount in the mold can be found by measuring the temperature distribution of the mold. If the mold stores heat, the mold made of cast or mold steel expands thermally, and therefore the distance between the upper and lower molds of the mold manufactured by providing a gap of a normal plate thickness varies. Thus, if the gap between the die surface and the fold pressing portion is smaller than the plate thickness, the inflow amount of the material is reduced, and thus the risk of occurrence of cracks is increased. The forming load during press forming can be measured by a load cell (load cell) or other load meter provided directly between the press body, the slide of the press, and the die, in the die, or the like. If a crack occurs, the forming load is reduced, noise is generated in the forming load, or the forming load distribution in the mold is changed, so that the presence or absence of the occurrence of the crack can be detected.
In the step after press forming, the area of the light leakage to the opposite surface due to the crack when the crack is generated is measured by using an irradiation device that irradiates the entire surface of the press-formed member with light such as laser light and a light receiving device that receives light from the opposite surface, whereby the presence or absence of the crack can be measured. Further, by attaching a strain gauge to a die during press forming, the strain of the die can be measured. If a crack is generated, a slight amount of deformation occurs depending on the location of the die, and therefore it is possible to detect at which position in the press-formed part the crack is generated.
TABLE 1
(Table 1)
As shown in table 2 below, the occurrence of cracks can be suppressed by changing the forming operation of the servo press machine, the wrinkle pressing pressure of the servo die cushion, the wrinkle pressing standby position, the pressure of the movable die in the die, the standby position, the height of the spacer, the material installation position, lubrication, and the material temperature. The sliding operation in the usual press forming is a crank operation based on uniform circular motion, but by decelerating the forming speed immediately before the forming bottom dead center or stopping the sliding operation a plurality of times in the middle of the bottom dead center stroke and performing the forming, the occurrence of cracks can be suppressed.
Further, by the servo die cushion portion, the wrinkle pressing force during the drawing forming is reduced or the wrinkle pressing standby position is lowered, whereby the inflow amount of the material is increased, and the occurrence of cracks can be suppressed. In addition, by reducing the pressure of the movable mold in the mold or reducing the standby position of the movable mold, the outflow of the material increases, and the occurrence of cracks can be suppressed. In addition, by locally increasing the height of the spacer provided in the die, for example, the gap between the die surface and the fold pressing portion is locally increased to a plate thickness or more, the inflow amount of the material can be increased, and therefore, the occurrence of cracks can be suppressed.
When the coil material C is moved from the standard position to the die arrangement position during conveyance, the balance of the material inflow amount changes during press forming, and cracks occur. Therefore, the occurrence of cracks can be suppressed by disposing the coil material C at the standard disposition position. In the pretreatment apparatus, the coil C or the die is oiled by the oil jet before press forming, and thus the inflow amount of the material increases during drawing forming or the like, and therefore, the occurrence of cracks can be suppressed. In addition, at a portion where cracks may occur, the coil C is locally heated by a laser heater or the like before press forming, whereby ductility of the coil C is improved, and occurrence of cracks can be suppressed.
TABLE 2
(Table 2)
[ embodiment 3 ]
In embodiment 3, the arithmetic device 122 obtains the directionality of the press forming condition for suppressing the occurrence of wrinkles in the coil material C based on the result of prediction of the press forming result. The computing device 122 compensates for the error in the predicted value of the press forming result based on the analysis result of the actual result value of the mass production press, and corrects the press forming condition in the direction in which the occurrence of wrinkles in the coil C is suppressed. As the complement method, a method of experimentally obtaining in advance a complement coefficient calculated by an error between a prediction result and an actual result value based on the CAE technique, a method via a machine learning model aiming at minimizing the error, and the like can be exemplified. The arithmetic device 122 stores data of press forming results corresponding to the material characteristics of the coil material C and the corrected press forming conditions in the database 121.
The arithmetic device 122 performs statistical analysis using data such as the material property value of the coil C, the press forming condition, and the actual press forming result, analyzes the relationship between the material property value of the coil C, the press forming condition, and the press forming result, and stores the analysis result in the database 121. The computing device 122 generates a machine learning model that takes the input information as described above as input and takes press forming conditions for suppressing the occurrence of wrinkles in the coil C as output by a method such as artificial intelligence or machine learning using data stored in the database 121. The computing device 122 inputs the input information into the machine learning model according to a calculation instruction of the press forming condition for suppressing the occurrence of wrinkles in the coil C, thereby calculating the press forming condition for suppressing the occurrence of wrinkles in the coil C corresponding to the input information. Examples of the press forming conditions that are calculated include forming load, forming operation, and wrinkle pressing force. The control device 12 performs feedback control on at least one of the servo press 8 and the preprocessing device 14 provided downstream of the punching process based on the calculated press forming conditions.
Further, the material property value of the coil material C is greatly affected by, in particular, yield strength and tensile strength, with respect to the occurrence of wrinkles. Therefore, the control device 12 calculates appropriate press forming conditions by measuring and analyzing the fluctuation of the material characteristic value before press forming, and suppresses the occurrence of wrinkles by feedforward control. In the present embodiment, the control device 12 estimates the strength-related material characteristics such as Yield Strength (YS) and Tensile Strength (TS) by correlating the measured value of the material strength measured on line with the manufacturing information of the material by using an artificial intelligence or machine learning method or the like. The information on the material strength at this time can be measured by measuring the shear load at the time of punching the material or measuring the residual magnetic field after applying a pulse magnetic field to the material before punching, as shown in table 3 below.
On the other hand, if wrinkles occur, measured values of the image, the patch pattern, the shape, and the like of the coil C change during or after press molding. Therefore, the control device 12 calculates appropriate press forming conditions by measuring the fluctuation of the measured value, predicting and analyzing the trend thereof, and suppresses the occurrence of wrinkles by feedback control. In addition to the capability of capturing an image of the press-formed member with a camera and detecting shadows of the formed member by image analysis to directly detect the presence or absence of wrinkles, the variation in inflow amount of the material can be detected by image analysis of the contour of the edge of the material after drawing. The higher the inflow amount of the material, the higher the risk of occurrence of wrinkles, and therefore, the sign of occurrence of wrinkles can also be detected. Further, the position and degree of deformation of the surface can be measured by irradiating the surface of the press-molded member with stripe patterns at equal intervals by a light source such as illumination, and performing image analysis on the reflected stripe patterns. Further, by measuring the three-dimensional shape and the two-dimensional shape of the press-molded member by the shape measuring device, the irregularities associated with wrinkles on the surface of the press-molded member can be directly measured.
TABLE 3
(Table 3)
As shown in table 4 below, the occurrence of wrinkles can be suppressed by changing the forming load of the servo press machine, the wrinkle pressing force of the servo die cushion portion, and the wrinkle pressing standby position, or by changing the pressure of the movable die, the standby position, and the height of the distance block by the press forming die. A typical press machine can only slide with a preset stroke, but the stroke can be changed online by using a servo press machine. By further increasing the stroke by several mm with respect to the preset bottom dead center stroke, the forming load increases, and the generated wrinkles are flattened, thereby suppressing the generation of wrinkles. Further, by increasing the wrinkle pressing force of the drawing forming by the servo die cushion portion or by increasing the wrinkle pressing standby position, the inflow amount of the material is reduced, and generation of wrinkles can be suppressed. Further, by increasing the pressure of the movable die (gasket) in the die or increasing the standby position of the movable die, the outflow amount of the material increases, and the occurrence of wrinkles can be suppressed. In addition, by locally reducing the height of the spacer blocks provided in the die, for example, the gap between the die surface and the wrinkle pressing portion is locally reduced to a plate thickness or less, and the inflow amount of the material can be reduced, so that the occurrence of wrinkles can be suppressed.
TABLE 4
(Table 4)
[ embodiment 4]
In embodiment 4, the arithmetic device 122 obtains the directionality of the press forming condition for suppressing occurrence of the dimensional accuracy failure of the press-formed member based on the prediction result of the press forming result. The computing device 122 corrects the press forming conditions in a direction to suppress occurrence of dimensional accuracy failure of the press-formed member by compensating for an error in a predicted value of the press forming result based on an analysis result of the actual value of the mass-produced press. As the complement method, a method of experimentally obtaining in advance a complement coefficient calculated by an error between a prediction result and an actual result value based on the CAE technique, a method via a machine learning model aiming at minimizing the error, and the like can be exemplified. The arithmetic device 122 stores data of press forming results corresponding to the material characteristics of the coil material C and the corrected press forming conditions in the database 121.
The arithmetic device 122 performs statistical analysis using data such as the material property value of the coil C, the press forming condition, and the actual press forming result, analyzes the relationship between the material property value of the coil C, the press forming condition, and the press forming result, and stores the analysis result in the database 121. The computing device 122 generates a machine learning model that takes the input information as described above as input and takes press forming conditions for suppressing occurrence of dimensional accuracy failure of the press-formed part as output by means of artificial intelligence, machine learning, or the like using the data stored in the database 121. The computing device 122 inputs the input information to the machine learning model according to a calculation instruction of the press forming condition for suppressing occurrence of the dimensional accuracy failure of the press formed member, thereby calculating the press forming condition for suppressing occurrence of the dimensional accuracy failure of the press formed member corresponding to the input information. Examples of the press forming conditions to be calculated include forming load, forming operation, and wrinkle pressing force. The control device 12 performs feedback control on at least one of the servo press 8 and the preprocessing device 14 provided downstream of the punching process, based on the calculated press forming conditions.
Further, the mechanical properties of the coil material C such as Yield Strength (YS) and Tensile Strength (TS), the shape of the plate-like material, and the arrangement position of the forming die are greatly affected by the occurrence of dimensional accuracy defects. Therefore, the control device 12 calculates appropriate press forming conditions by measuring and analyzing the material characteristic value and the variation of the measured value before press forming, and suppresses the occurrence of dimensional accuracy failure by feed-forward control. In the present embodiment, the control device 12 estimates the strength-related material characteristics such as yield strength and tensile strength by correlating the measured value of the material strength measured on line with the manufacturing information of the material by using a method such as artificial intelligence or machine learning. The information on the material strength at this time can be measured by measuring the shear load at the time of punching the material or measuring the residual magnetic field after applying a pulse magnetic field to the material before punching, as shown in table 5 below. In addition, if the shape of the plate-like material varies, the dimensional accuracy of the press-formed member after press forming also varies. In particular, the higher the material strength, the greater the variation in the pressurization capability of the plate shape correcting device due to the shortage. Therefore, the shape of the plate-like material may be measured by a shape measuring device such as a two-dimensional laser displacement meter before press forming. In addition, when the arrangement position of the material to the forming die is changed, the balance of the shape of the press-formed member is changed, and thus the dimensional accuracy also changes. Therefore, the arrangement position of the material can also be measured by a laser displacement meter or the like.
On the other hand, if a dimensional accuracy defect occurs in the press-formed member, the shape of the press-formed member after press forming changes. Therefore, the control device 12 calculates appropriate press forming conditions by measuring the fluctuation of the measured value, predicting and analyzing the trend thereof, and suppresses the occurrence of dimensional accuracy failure by feedback control. In the process of transporting and inspecting the press-formed member after press forming, the one-dimensional shape, the two-dimensional shape, and the three-dimensional shape are measured by a displacement meter and a shape measuring device, and compared with the shape of a standard press-formed member, the position and the amount of deviation of the occurrence of the dimensional accuracy defect can be measured.
TABLE 5
(Table 5)
As shown in table 6 below, by changing the forming load and forming operation of the servo press, the wrinkle pressing force and the wrinkle pressing standby position of the servo die cushion are changed, the pressure and standby position of the movable die by the press forming die are changed, and the height of the distance block is changed, so that the cam bending amount by the cam mechanism, the position of the material to be placed during conveyance, and the like are changed, and the occurrence of dimensional accuracy defects can be suppressed. Further, although a usual press machine can slide only with a stroke set in advance, the stroke can be changed on line by using a servo press machine. Further, by further increasing and decreasing the number of mm strokes with respect to the preset bottom dead center stroke, the forming load increases and decreases, and the elastic strain amount of the forming die and the deformation amount of the formed member change, so that the dimensional accuracy can be changed.
Further, although the usual press forming sliding operation is a crank operation based on uniform circular motion, the dimensional accuracy can be changed by decelerating the forming speed immediately before forming the bottom dead center or stopping the sliding operation a plurality of times during the bottom dead center stroke to perform forming, and the shape balance of the press-formed member is changed. Further, by changing the wrinkle pressing force or the wrinkle pressing standby position of the drawing forming by the servo die cushion portion, the inflow amount of the material is increased or decreased, and the shape balance of the press-formed member is changed, thereby changing the dimensional accuracy.
In addition, by changing the pressure of the movable die (pad) in the die or the standby position of the movable die, the dimensional accuracy is also changed by changing the shape balance of the press-formed member. In addition, by locally changing the height of the spacer provided in the die, for example, the gap between the die surface and the fold pressing portion can be locally changed. Further, since the bottom dead center stroke can be changed, the shape balance of the press-formed member can be changed, and the dimensional accuracy can be changed. In addition, by making the die have a cam bending structure using a cam mechanism, the bending amount of the press-formed member can be changed, and therefore, the dimensional accuracy can be changed. In addition, when the material is set to the die in the next step during transportation, the balance of the shape of the press-formed member after press forming changes when the setting position changes, and therefore, the dimensional accuracy can be changed.
[ embodiment 5 ]
The control device 122 of embodiment 5 is applied to the press line 1 shown in fig. 5 and 6. In the present embodiment, the computing device 122 obtains the directionality of the press forming condition that suppresses the occurrence of die damage and surface quality failure of the press-formed member accompanying the die damage, based on the prediction result of the press forming result. The computing device 122 compensates for the error in the predicted value of the press forming result based on the analysis result of the actual value of the mass-produced press forming, thereby correcting the press forming condition in a direction in which the occurrence of die damage and surface quality defects of the press-formed member associated with the die damage are suppressed. As the complement method, a method of experimentally obtaining in advance a complement coefficient calculated by an error between a prediction result and an actual result value based on the CAE technique, a method via a machine learning model aiming at minimizing the error, and the like can be exemplified. The arithmetic device 122 stores data of press forming results corresponding to the material characteristics of the coil material C and the corrected press forming conditions in the database 121.
The arithmetic device 122 performs statistical analysis using data such as the material property value of the coil C, the press forming condition, and the actual press forming result, analyzes the relationship between the material property value of the coil C, the press forming condition, and the press forming result, and stores the analysis result in the database 121. The computing device 122 generates a machine learning model that takes the input information as an input and takes press forming conditions that suppress occurrence of die damage and surface quality defects of press-formed members associated with the die damage as an output by means of artificial intelligence, machine learning, or the like using data stored in the database 121. The computing device 122 inputs the input information to the machine learning model according to a calculation instruction of the press forming condition for suppressing occurrence of the die damage and the surface quality failure of the press formed member due to the die damage, thereby calculating the press forming condition for suppressing occurrence of the die damage and the surface quality failure of the press formed member due to the die damage corresponding to the input information. Examples of the press forming conditions to be calculated include forming load, forming operation, and wrinkle pressing force. The control device 12 performs feedback control on at least one of the servo press 8 and the preprocessing device 14 provided downstream of the punching process based on the calculated press forming conditions.
In addition, if die damage and surface quality defects of the press-formed member associated with the die damage occur, measured values such as images, forming load, vibration, and temperature change during or after press forming. Therefore, the control device 12 calculates appropriate press forming conditions by measuring the fluctuation of the measured value, predicting and analyzing the trend thereof, and suppresses the occurrence of die damage and surface quality defects of the press formed member associated with the die damage by feedback control. Specifically, as shown in table 7 below, the change in the inflow amount of the material can be detected by capturing an image of the press-formed member after press forming with a camera and analyzing the contour of the edge portion of the press-formed member after drawing. In mass production press forming, if die damage occurs, frictional resistance of the die surface against the material and the fold pressing portion against the material increases, and inflow amount of the material decreases, so that occurrence of die damage can be indirectly detected. Further, by directly photographing the press-formed member and performing image analysis on the brightness and the like of the surface, it is possible to directly detect the surface quality defect associated with the die damage. The forming load during press forming can be measured by load cell or other load cell provided in the press body, between the slide of the press and the die, and in the die. Since noise is added to the waveform of the normal forming load when the die damage occurs, the occurrence of the die damage can be detected by measuring the fluctuation of the forming load during press forming. Further, vibration during press forming can be measured by Acoustic Emission (AE) or the like. If the mold damage occurs, noise vibration that cannot be observed in normal times can be detected, and therefore the mold damage can be detected. Further, when the temperature of the mold during or after press forming is measured by a thermal imager, a non-contact thermometer, or the like, the temperature distribution on the surface of the mold can be measured. In general, a molding die is subjected to surface coating treatment in order to prevent damage to the die surface. For example, the surface coating is composed of a compound such as TiC or CrN, and the characteristic of the compound is a heat-resistant temperature. In mass production press forming, if the heat is stored in the die and press forming is continued in a state where the heat-resistant temperature of the surface coating is exceeded, peeling of the surface coating and damage to the die as a base material are caused. Therefore, mold damage can also be indirectly detected by measuring the temperature of the mold.
TABLE 7
(Table 7)
As shown in table 8 below, by changing the molding operation of the servo press machine or by applying oil to the coil material C before press molding using the pretreatment device 14, it is possible to suppress the occurrence of die damage and surface quality defects of the press-molded member associated with the die damage. The usual press forming sliding operation is a crank operation based on uniform circular motion, but the press forming is performed by decelerating the forming speed immediately before forming the bottom dead center or stopping the sliding operation a plurality of times in the middle of the bottom dead center stroke, whereby the damage when the coil C contacts the die is reduced, and the heat generation amount at the time of processing can be reduced. This can suppress occurrence of die damage and surface quality failure of the press-formed member due to the die damage. Further, by oiling the coil C or the die before press forming with the oil sprayer in the pretreatment device, lubricity between the coil C and the die improves, and heat generation during processing can be suppressed. This can suppress occurrence of die damage and surface quality failure of the press-formed member due to the die damage.
TABLE 8
(Table 8)
The present invention has been described above with reference to the embodiments to which the invention completed by the present inventors has been applied, but the present invention is not limited by the description and drawings forming a part of the disclosure of the present embodiment. That is, other embodiments, examples, operation techniques, and the like, which are performed by those skilled in the art based on the present embodiment, are all included in the scope of the present invention.
Industrial applicability
According to the present invention, a press line that can suppress occurrence of defective forming without requiring much labor and cost can be provided. Further, according to the present invention, it is possible to provide a press forming condition calculation method and a press forming condition calculation program capable of calculating press forming conditions that suppress occurrence of forming failure. Further, according to the present invention, it is possible to provide a press line that can suppress occurrence of cracks in a metal material without requiring much labor and cost. Further, according to the present invention, it is possible to provide a press forming condition calculation method and a press forming condition calculation program capable of calculating press forming conditions that suppress occurrence of cracks in a metal material. Further, according to the present invention, a press line that can suppress the occurrence of wrinkles in a metal material without requiring much labor and cost can be provided. Further, according to the present invention, it is possible to provide a press forming condition calculation method and a press forming condition calculation program capable of calculating press forming conditions that suppress occurrence of wrinkles in a metal material. Further, according to the present invention, it is possible to provide a press line in which occurrence of dimensional accuracy defects of press-formed members can be suppressed without requiring much labor and cost. Further, another object of the present invention is to provide a press-forming condition calculation method and a press-forming condition calculation program capable of calculating press-forming conditions that suppress occurrence of dimensional accuracy failure of a press-formed member. Further, according to the present invention, it is possible to provide a press line capable of suppressing occurrence of die damage and surface quality failure of press-formed members due to die damage without requiring much labor and cost. Further, according to the present invention, it is possible to provide a press forming condition calculation method and a press forming condition calculation program capable of calculating press forming conditions that suppress occurrence of die damage and surface quality defects of a press formed member associated with the die damage.
Description of the reference numerals
1. Stamping line; 2. an uncoiler; 3, uncoiling the straightener; 4. a blanking die; handling means; forming a mold; mechanical punching machine; servo punching machine; sensors; 12. 12a, 12 b..control means; material manufacturing plant; pretreatment device; a transmitting device; a receiving device; database; an arithmetic device; c. coiled material; press forming the part.
Claims (27)
1. A press line is characterized by comprising:
a first punch that shears an outer peripheral portion of a metal material using a blanking die;
a second punch that forms a press-formed part by press-forming the metal material sheared by the first punch using a forming die;
a pretreatment device provided downstream of the first press machine and configured to perform a predetermined pretreatment on the metal material;
a measurement unit that measures information related to a material characteristic value of the metal material before the press forming; and
and a control device that calculates press forming conditions for suppressing occurrence of forming failure for the metal material to be formed by inputting the material characteristic value and the manufacturing information of the metal material to be formed measured by the measuring means into a machine learning model that is input with the material characteristic value and the manufacturing information of the metal material to be formed and output with the press forming conditions for suppressing occurrence of forming failure for the metal material to be formed, and performs feed-forward control for at least one of the second press machine and the pretreatment device based on the calculated press forming conditions.
2. A press line is characterized by comprising:
a first punch that shears an outer peripheral portion of a metal material using a blanking die;
a second punch that forms a press-formed part by press-forming the metal material sheared by the first punch using a forming die;
a pretreatment device provided downstream of the first press machine and configured to perform a predetermined pretreatment on the metal material;
a measuring unit that measures information related to the metal material during or after press forming; and
and a control device that calculates press forming conditions for suppressing occurrence of forming failure for a subsequent metal material by inputting information on the metal material during press forming or after press forming into a machine learning model that is input with information on the metal material during press forming or after press forming and that is output with press forming conditions for suppressing occurrence of forming failure for the metal material, and that feedback-controls at least one of the second press machine and the pretreatment device based on the calculated press forming conditions.
3. A press line is characterized by comprising:
a first punch that shears an outer peripheral portion of a metal material using a blanking die;
a second punch that forms a press-formed part by press-forming the metal material sheared by the first punch using a forming die;
a pretreatment device provided downstream of the first press machine and configured to perform a predetermined pretreatment on the metal material;
a measuring unit that measures a residual magnetic field of the metal material before shearing by the first punch and/or a shearing load of the metal material during shearing by the first punch; and
and a control device that calculates a press forming condition for suppressing occurrence of cracks in a metal material to be formed by inputting a residual magnetic field of the metal material before the cutting by the first press and/or a cutting load of the metal material and manufacturing information of the metal material during the cutting by the first press, and inputting a residual magnetic field of the metal material before the cutting by the first press and/or a cutting load of the metal material during the cutting by the first press and manufacturing information of the metal material, which are measured by the measuring means, into a machine learning model that outputs press forming conditions of the metal material for suppressing occurrence of cracks in the metal material, and performs feedforward control on at least one of the second press and the pretreatment device based on the calculated press forming conditions.
4. A press line is characterized by comprising:
a first punch that shears an outer peripheral portion of a metal material using a blanking die;
a second punch that forms a press-formed part by press-forming the metal material sheared by the first punch using a forming die;
a pretreatment device provided downstream of the first press machine and configured to perform a predetermined pretreatment on the metal material;
a measuring unit that measures information related to the metal material during or after press forming; and
and a control device that calculates press forming conditions for suppressing occurrence of cracks for a subsequent metal material by inputting information on the metal material during press forming or after press forming, to a machine learning model that is input with information on the metal material during press forming or after press forming and that is output with press forming conditions for suppressing occurrence of cracks for the metal material, and that performs feedback control for at least one of the second press machine and the pretreatment device based on the calculated press forming conditions.
5. A press line is characterized by comprising:
a first punch that shears an outer peripheral portion of a metal material using a blanking die;
a second punch that forms a press-formed part by press-forming the metal material sheared by the first punch using a forming die;
a pretreatment device provided downstream of the first press machine and configured to perform a predetermined pretreatment on the metal material;
a measuring unit that measures a residual magnetic field of the metal material before shearing by the first punch and/or a shearing load of the metal material during shearing by the first punch; and
and a control device that calculates press forming conditions for suppressing occurrence of wrinkles of a metal material to be formed and performs feed-forward control of at least one of the second press and the pretreatment device based on the calculated press forming conditions, by inputting a residual magnetic field of the metal material before cutting by the first press and/or a shear load of the metal material during cutting by the first press and manufacturing information of the metal material, which are measured by the measurement unit, into a machine learning model that takes as input a shear load of the metal material and manufacturing information of the metal material during cutting by the first press and takes as output press forming conditions of the metal material for suppressing occurrence of wrinkles of the metal material.
6. A press line is characterized by comprising:
a first punch that shears an outer peripheral portion of a metal material using a blanking die;
a second punch that forms a press-formed part by press-forming the metal material sheared by the first punch using a forming die;
a pretreatment device provided downstream of the first press machine and configured to perform a predetermined pretreatment on the metal material;
a measuring unit that measures information related to the metal material during or after press forming; and
and a control device that calculates press forming conditions for suppressing occurrence of wrinkles for a subsequent metal material by inputting information on the metal material during press forming or after press forming, and feedback-controls at least one of the second press machine and the pretreatment device based on the calculated press forming conditions, to a machine learning model that is input with information on the metal material during press forming or after press forming and that is output with press forming conditions for suppressing occurrence of wrinkles of the metal material.
7. A press line is characterized by comprising:
a first punch that shears an outer peripheral portion of a metal material using a blanking die;
a second punch that forms a press-formed part by press-forming the metal material sheared by the first punch using a forming die;
a pretreatment device provided downstream of the first press machine and configured to perform a predetermined pretreatment on the metal material;
a measuring unit that measures at least one of a residual magnetic field of the metal material before shearing by the first punch, a shearing load of the metal material during shearing by the first punch, a shape of the metal material before shearing by the second punch, and a placement position of the metal material with respect to the forming die; and
a control device that calculates press forming conditions for suppressing occurrence of dimensional defects of the press-formed parts for a metal material to be formed by using as input at least one of a shape of the metal material before shearing by the first press, a shearing load of the metal material before shearing by the first press, a placement position of the metal material with respect to the forming die, and manufacturing information of the metal material, and inputs a machine learning model in which press forming conditions for the metal material are output, the machine learning model being used as a basis for which press forming conditions for suppressing occurrence of dimensional defects of the press-formed parts are output, the machine learning model being used as a basis for calculating at least one of the press forming conditions for suppressing occurrence of dimensional defects of the press-formed parts, the shearing load of the metal material before shearing by the first press, the shape of the metal material before shearing by the second press, and the manufacturing information of the metal material to be formed by the forming die, the press-forming conditions being used as a basis for controlling press forming conditions for the press-forming by the first press-formed parts, the press forming conditions being calculated by the basis of at least one of the first press-formed conditions.
8. A press line is characterized by comprising:
a first punch that shears an outer peripheral portion of a metal material using a blanking die;
a second punch that forms a press-formed part by press-forming the metal material sheared by the first punch using a forming die;
a pretreatment device provided downstream of the first press machine and configured to perform a predetermined pretreatment on the metal material;
a measurement unit that measures information related to a shape of the press-formed part; and
and a control device that calculates press forming conditions for suppressing occurrence of dimensional accuracy failure of the press-formed member for a subsequent metal material by inputting information on the shape of the press-formed member measured by the measurement means into a machine learning model that is input with information on the shape of the press-formed member and output with press forming conditions for suppressing occurrence of dimensional accuracy failure of the press-formed member for the metal material, and performs feedback control for at least one of the second press machine and the pretreatment device based on the calculated press forming conditions.
9. A press line is characterized by comprising:
a first punch that shears an outer peripheral portion of a metal material using a blanking die;
a second punch that forms a press-formed part by press-forming the metal material sheared by the first punch using a forming die;
a pretreatment device provided downstream of the first press machine and configured to perform a predetermined pretreatment on the metal material;
a measuring unit that measures information related to the metal material during or after press forming; and
and a control device that calculates, for a subsequent metal material, a press forming condition that suppresses occurrence of die damage and surface quality failure of a press-formed member due to die damage by inputting information on the metal material during or after press forming measured by the measuring means to a machine learning model that is input with information on the metal material during or after press forming and that is output with respect to a press forming condition that suppresses occurrence of die damage and surface quality failure of a press-formed member due to die damage, and that performs feedback control for at least one of the second press and the preprocessing device based on the calculated press forming condition.
10. A method for calculating press forming conditions is characterized in that,
the method comprises the following steps: the press forming conditions for suppressing the occurrence of forming failure are calculated for the metal material to be formed by inputting the material characteristic value and the manufacturing information of the metal material to be formed into a machine learning model which is inputted with the material characteristic value and the manufacturing information of the metal material and which is outputted with the press forming conditions for suppressing the occurrence of forming failure of the metal material.
11. A method for calculating press forming conditions is characterized in that,
the method comprises the following steps: the press forming conditions for suppressing the occurrence of forming defects are calculated for a metal material to be formed by inputting information on the metal material during or after press forming and inputting information on the metal material during or after press forming into a machine learning model which is inputted with information on the press forming conditions for suppressing the occurrence of forming defects for the metal material and outputting the press forming conditions for suppressing the occurrence of forming defects.
12. A method for calculating press forming conditions is characterized in that,
the method comprises the following steps: the method includes the step of calculating a press forming condition for suppressing occurrence of a crack for a metal material to be formed by inputting a residual magnetic field of the metal material before cutting by a punch for cutting an outer peripheral portion of the metal material using a punching die and/or a cutting load of the metal material and manufacturing information of the metal material during cutting by the punch, and by inputting a machine learning model which outputs a press forming condition of the metal material for suppressing occurrence of a crack for the metal material, and by inputting a residual magnetic field of the metal material before cutting by the punch and/or a cutting load of the metal material and manufacturing information of the metal material during cutting by the punch.
13. A method for calculating press forming conditions is characterized in that,
the method comprises the following steps: the method includes the steps of inputting information related to a metal material during or after press forming, and inputting information related to the metal material during or after press forming into a machine learning model which is output by taking as a press forming condition of the metal material for suppressing occurrence of cracks in the metal material, thereby calculating press forming conditions for suppressing occurrence of cracks in a subsequent metal material.
14. A method for calculating press forming conditions is characterized in that,
the method comprises the following steps: the press forming conditions for suppressing the occurrence of wrinkles in a metal material to be formed are calculated by inputting a residual magnetic field of the metal material before shearing by a punch for shearing an outer peripheral portion of the metal material and/or a shearing load of the metal material and manufacturing information of the metal material during shearing by the punch, and inputting a machine learning model for outputting press forming conditions of the metal material for suppressing the occurrence of wrinkles in the metal material, with respect to the metal material to be formed.
15. A method for calculating press forming conditions is characterized in that,
the method comprises the following steps: the press forming conditions for suppressing the occurrence of wrinkles in the subsequent metal material are calculated by inputting information on the metal material during or after press forming into a machine learning model which is inputted with information on the metal material during or after press forming and outputted with press forming conditions for suppressing the occurrence of wrinkles in the metal material.
16. A method for calculating press forming conditions is characterized in that,
the method comprises the following steps: the method includes the steps of calculating a press forming condition of a metal forming member by inputting a residual magnetic field of the metal material before shearing by a first press that shears an outer peripheral portion of the metal material using a punching die, a shearing load of the metal material during shearing by the first press, a shape of the metal material before shearing by a second press that forms a press forming member by press forming the metal material sheared by the first press using a forming die, and manufacturing information of the metal material and at least one of a layout position of the metal material with respect to the forming die, and manufacturing information of the metal material, and by inputting a machine learning model in which a press forming condition of the metal material is output, in which occurrence of dimensional accuracy failure of the press forming member is suppressed, of the residual magnetic field of the metal material before shearing by the first press, a shearing load of the metal material during shearing by the first press, a shape of the metal material before shearing by the second press, and manufacturing information of the metal material with respect to at least one of the layout position of the forming die are calculated, and thus occurrence of dimensional accuracy of the press forming member is suppressed.
17. A method for calculating press forming conditions is characterized in that,
the method comprises the following steps: the press-forming conditions for suppressing occurrence of dimensional accuracy failure of the press-formed member are calculated for the subsequent metal material by inputting information on the shape of the press-formed member after press-forming into a machine learning model which is inputted with information on the shape of the press-formed member formed by press-forming the metal material using a forming die and which is outputted with press-forming conditions of the metal material for suppressing occurrence of dimensional accuracy failure of the press-formed member.
18. A method for calculating press forming conditions is characterized in that,
the method comprises the following steps: the method includes the steps of inputting information related to a metal material during or after press forming, and inputting information related to the metal material during or after press forming into a machine learning model which is output by taking as a press forming condition for suppressing occurrence of die damage and surface quality defects of the press formed member accompanying the die damage, thereby calculating press forming conditions for suppressing occurrence of die damage and surface quality defects of the press formed member accompanying the die damage for a subsequent metal material.
19. A press forming condition calculation program is characterized in that,
causing the computer to execute the following process: the press forming conditions for suppressing the occurrence of forming failure are calculated for the metal material to be formed by inputting the material characteristic value and the manufacturing information of the metal material to be formed into a machine learning model which is inputted with the material characteristic value and the manufacturing information of the metal material and which is outputted with the press forming conditions for suppressing the occurrence of forming failure of the metal material.
20. A press forming condition calculation program is characterized in that,
causing the computer to execute the following process: the press forming conditions for suppressing the occurrence of forming defects are calculated for a metal material to be formed by inputting information on the metal material during or after press forming and inputting information on the metal material during or after press forming into a machine learning model which is inputted with information on the press forming conditions for suppressing the occurrence of forming defects for the metal material and outputting the press forming conditions for suppressing the occurrence of forming defects.
21. A press forming condition calculation program is characterized in that,
causing the computer to execute the following process: the method includes the step of calculating a press forming condition for suppressing occurrence of a crack for a metal material to be formed by inputting a residual magnetic field of the metal material before cutting by a punch for cutting an outer peripheral portion of the metal material using a punching die and/or a cutting load of the metal material and manufacturing information of the metal material during cutting by the punch, and by inputting a machine learning model which outputs a press forming condition of the metal material for suppressing occurrence of a crack for the metal material, and by inputting a residual magnetic field of the metal material before cutting by the punch and/or a cutting load of the metal material and manufacturing information of the metal material during cutting by the punch.
22. A press forming condition calculation program is characterized in that,
causing the computer to execute the following process: the method includes the steps of inputting information related to a metal material during or after press forming, and inputting information related to the metal material during or after press forming into a machine learning model which is output by taking as a press forming condition of the metal material for suppressing occurrence of cracks in the metal material, thereby calculating press forming conditions for suppressing occurrence of cracks in a subsequent metal material.
23. A press forming condition calculation program is characterized in that,
causing the computer to execute the following process: the press forming conditions for suppressing the occurrence of wrinkles in a metal material to be formed are calculated by inputting a residual magnetic field of the metal material before shearing by a punch for shearing an outer peripheral portion of the metal material and/or a shearing load of the metal material and manufacturing information of the metal material during shearing by the punch, and inputting a machine learning model for outputting press forming conditions of the metal material for suppressing the occurrence of wrinkles in the metal material, with respect to the metal material to be formed.
24. A press forming condition calculation program is characterized in that,
causing the computer to execute the following process: the press forming conditions for suppressing the occurrence of wrinkles in the subsequent metal material are calculated by inputting information on the metal material during or after press forming into a machine learning model which is inputted with information on the metal material during or after press forming and outputted with press forming conditions for suppressing the occurrence of wrinkles in the metal material.
25. A press forming condition calculation program is characterized in that,
causing the computer to execute the following process: the method includes the steps of calculating a press forming condition of a metal forming member by inputting a residual magnetic field of the metal material before shearing by a first press that shears an outer peripheral portion of the metal material using a punching die, a shearing load of the metal material during shearing by the first press, a shape of the metal material before shearing by a second press that forms a press forming member by press forming the metal material sheared by the first press using a forming die, and manufacturing information of the metal material and at least one of a layout position of the metal material with respect to the forming die, and manufacturing information of the metal material, and by inputting a machine learning model in which a press forming condition of the metal material is output, in which occurrence of dimensional accuracy failure of the press forming member is suppressed, of the residual magnetic field of the metal material before shearing by the first press, a shearing load of the metal material during shearing by the first press, a shape of the metal material before shearing by the second press, and manufacturing information of the metal material with respect to at least one of the layout position of the forming die are calculated, and thus occurrence of dimensional accuracy of the press forming member is suppressed.
26. A press forming condition calculation program is characterized in that,
causing the computer to execute the following process: the press-forming conditions for suppressing occurrence of dimensional accuracy failure of the press-formed member are calculated for the subsequent metal material by inputting information on the shape of the press-formed member after press-forming into a machine learning model which is inputted with information on the shape of the press-formed member formed by press-forming the metal material using a forming die and which is outputted with press-forming conditions of the metal material for suppressing occurrence of dimensional accuracy failure of the press-formed member.
27. A press forming condition calculation program is characterized in that,
causing the computer to execute the following process: the method includes the steps of inputting information related to a metal material during or after press forming, and inputting information related to the metal material during or after press forming into a machine learning model which is output by taking as a press forming condition for suppressing occurrence of die damage and surface quality defects of the press formed member accompanying the die damage, thereby calculating press forming conditions for suppressing occurrence of die damage and surface quality defects of the press formed member accompanying the die damage for a subsequent metal material.
Applications Claiming Priority (7)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2021-034440 | 2021-03-04 | ||
| JP2021-034439 | 2021-03-04 | ||
| JP2021034441 | 2021-03-04 | ||
| JP2021-034161 | 2021-03-04 | ||
| JP2021-034441 | 2021-03-04 | ||
| JP2021-034162 | 2021-03-04 | ||
| PCT/JP2022/009139 WO2022186337A1 (en) | 2021-03-04 | 2022-03-03 | Press line, press forming condition calculation method, and press forming condition calculation program |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117015448A true CN117015448A (en) | 2023-11-07 |
Family
ID=88571315
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202280018559.XA Pending CN117015448A (en) | 2021-03-04 | 2022-03-03 | Press line, press forming condition calculation method, and press forming condition calculation program |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117015448A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118386587A (en) * | 2024-07-01 | 2024-07-26 | 金丰（中国）机械工业有限公司 | Load correction method for multipoint eccentric driving mechanism of press |
-
2022
- 2022-03-03 CN CN202280018559.XA patent/CN117015448A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118386587A (en) * | 2024-07-01 | 2024-07-26 | 金丰（中国）机械工业有限公司 | Load correction method for multipoint eccentric driving mechanism of press |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP2025425B1 (en) | Press-forming method, press-forming device, computer program product and computer readable recording medium | |
| JPWO2010041662A1 (en) | Method, apparatus, program, and recording medium for determining cracks in metal press-formed products | |
| US20100154968A1 (en) | Method and production line for laminate assembly | |
| CN117015448A (en) | Press line, press forming condition calculation method, and press forming condition calculation program | |
| JP4943284B2 (en) | Thin plate press forming equipment | |
| JP7081690B2 (en) | Manufacturing method of press-molded products and press line | |
| CN113365750B (en) | Method for manufacturing press-formed article and press line | |
| JPH10166059A (en) | Plate bending method | |
| WO2022186337A1 (en) | Press line, press forming condition calculation method, and press forming condition calculation program | |
| CN116618529B (en) | Control system and method for intelligent die | |
| KR101042056B1 (en) | Curved surface forming method of a steel plate using a variable type of metal mold | |
| CN117597638A (en) | Method for operating a press, computer program and electronically readable data carrier | |
| JP2009095877A (en) | Apparatus and method for press-forming sheet metal | |
| CN115194024B (en) | Design modeling method based on upper wedge mechanism of stamping die | |
| Tovmasyan et al. | Comprehensive study of the shaping of the near-edge zone in flat rolled products during the production of pipes for main pipelines using modern calculation and measurement methods | |
| Wang et al. | Study on flexible bending process of sheet metal and its production equipment | |
| CN117260265A (en) | Automobile brake piston production method and system | |
| CN117787052A (en) | Method for predicting abrasion of insert of hot stamping die | |
| CN115673111A (en) | Controllable and adjustable stamped draw bead with inverted bead geometry | |
| CN118650323A (en) | Welding reinforcing method for thin metal plate | |
| JP2023102256A (en) | Method, device, and program for evaluating peripheral shape of press formed item, and method for manufacturing press formed item | |
| CN118265956A (en) | Method for optimizing a forming process for forming a workpiece and forming device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |