CN117893885A - Method, device and system for correcting defect detection precision of composite metal foil - Google Patents
Method, device and system for correcting defect detection precision of composite metal foil Download PDFInfo
- Publication number
- CN117893885A CN117893885A CN202410097545.2A CN202410097545A CN117893885A CN 117893885 A CN117893885 A CN 117893885A CN 202410097545 A CN202410097545 A CN 202410097545A CN 117893885 A CN117893885 A CN 117893885A
- Authority
- CN
- China
- Prior art keywords
- metal foil
- composite metal
- defect
- accuracy
- preset
- 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
- 239000011888 foil Substances 0.000 title claims abstract description 113
- 229910052751 metal Inorganic materials 0.000 title claims abstract description 113
- 239000002184 metal Substances 0.000 title claims abstract description 113
- 239000002131 composite material Substances 0.000 title claims abstract description 105
- 230000007547 defect Effects 0.000 title claims abstract description 95
- 238000001514 detection method Methods 0.000 title claims abstract description 79
- 238000000034 method Methods 0.000 title claims abstract description 30
- 230000006870 function Effects 0.000 claims abstract description 78
- 230000009471 action Effects 0.000 claims abstract description 13
- 230000003044 adaptive effect Effects 0.000 claims abstract description 8
- 230000006978 adaptation Effects 0.000 claims abstract description 6
- 238000012549 training Methods 0.000 claims abstract description 5
- 238000012937 correction Methods 0.000 claims description 10
- 230000007246 mechanism Effects 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 230000008859 change Effects 0.000 description 11
- 238000007599 discharging Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 230000035945 sensitivity Effects 0.000 description 4
- 238000005452 bending Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 239000011889 copper foil Substances 0.000 description 2
- 238000000151 deposition Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000007772 electroless plating Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000011179 visual inspection Methods 0.000 description 2
- 230000037303 wrinkles Effects 0.000 description 2
- 229920002799 BoPET Polymers 0.000 description 1
- JPVYNHNXODAKFH-UHFFFAOYSA-N Cu2+ Chemical compound [Cu+2] JPVYNHNXODAKFH-UHFFFAOYSA-N 0.000 description 1
- 229910052782 aluminium Inorganic materials 0.000 description 1
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 description 1
- 229910001431 copper ion Inorganic materials 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 229910021645 metal ion Inorganic materials 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000011148 porous material Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000001179 sorption measurement Methods 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
- 238000004804 winding Methods 0.000 description 1
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention provides a method, a device and a system for correcting defect detection precision of a composite metal foil, and belongs to the technical field of metal foil defect detection. The method comprises the following steps: acquiring image information of a preset area, a height value of a tension roller and a height difference of the preset area in the width direction; constructing an accuracy rewarding function item and a false alarm punishment function item according to the image information; constructing a shape adaptive reward function term according to the height value and the height difference; establishing an objective function according to the accuracy rewarding function item, the false alarm punishment function item and the shape adaptation rewarding function item; training a preset learning model by taking the optimized objective function as a target to obtain action space parameters of the preset learning model; determining corresponding target action space parameters according to the current height value and the height difference; and obtaining the current defect parameters of the composite metal foil according to a preset learning model corresponding to the target action space parameters. The invention can improve the defect detection precision of the composite metal foil.
Description
Technical Field
The application relates to the technical field of metal foil defect detection, in particular to a method, a device and a system for correcting defect detection precision of a composite metal foil.
Background
Composite metal foil is a thin composite material, and is generally prepared by depositing metal ions on the surface of a substrate in an electroless plating manner. For example, the composite copper foil can be prepared by depositing copper ions on the upper and lower surfaces of a micrometer-scale aluminum film or a PET film in an electroless plating mode, and the finally formed composite copper foil is a micrometer-scale ultrathin material. After the composite metal foil is prepared, defects on the surface of the composite metal foil, including defects such as pits, scratches, folds, pinholes, pores, edge breakage and tearing, are usually detected.
The high-precision visual inspection system is a common defect inspection scheme for inspecting composite metal foil, and generally, the defect information of the metal foil can be obtained by analyzing and processing the image information acquired by the visual inspection system.
Generally, in the prior art, a proper detection position is selected to detect defect information of the metal foil, but in the actual detection process, the flatness of the metal foil may be slightly changed, and in the prior art, a corresponding precision correction algorithm is not set for the change, so that the detection precision is reduced when the flatness of the metal foil is changed.
Disclosure of Invention
An object of the present invention is to provide a method for correcting defect detection accuracy of a composite metal foil, which can improve defect detection accuracy of a composite metal foil.
In particular, an embodiment of the present invention provides a method for correcting defect detection accuracy of a composite metal foil, where the composite metal foil is tensioned by a tension roller during detection, so that the composite metal foil has a preset tensioning force, and a vision system is disposed above a preset position of the composite metal foil, and is used for acquiring image information of a preset area of the composite metal foil, and the method includes:
acquiring image information of the preset area, a height value of the tension roller and a height difference of the preset area at two sides of the composite metal foil in the width direction;
constructing an accuracy rewarding function item and a false alarm punishment function item according to the image information;
constructing a shape-adaptive reward function term according to the height value and the height difference;
establishing an objective function according to the accuracy rewarding function item, the false alarm punishment function item and the shape adaptation rewarding function item;
training a preset learning model by taking the optimization of the objective function as a target to obtain action space parameters of the preset learning model, wherein the output of the preset learning model is a defect parameter of the composite metal foil;
determining corresponding target action space parameters according to the current height value and the height difference;
and obtaining the current defect parameters of the composite metal foil according to the preset learning model corresponding to the target action space parameters.
Optionally, the defect parameter is a defect size or a defect location.
Optionally, the shape-adaptive bonus function term c (t) in the step of constructing a shape-adaptive bonus function term from the height value and the height difference is determined according to the following formula:
where t represents time, h1 (t) represents the height value at time t, h2 (t) represents the height difference at time t, e is a natural constant, and a is an attenuation coefficient.
Optionally, in the step of constructing an accuracy reward function term and a false positive penalty function term according to the image information, the accuracy reward function term a (t) is determined according to the following formula:
a(t)＝TP(t)+TN(t)；
wherein TP (t) represents the first sample number of the true defects in the defect samples detected at the time t, and TN (t) represents the second sample number of the true normal surfaces in the normal surface samples detected at the time t.
Optionally, in the step of constructing the accuracy reward function term and the false alarm penalty function term according to the image information, the false alarm penalty function term FP (t) is a third sample number indicating that the defect sample detected at the time t is not a real defect.
Optionally, in the step of establishing an objective function according to the accuracy bonus function term, the false alarm penalty function term, and the shape adaptive bonus function term, the objective function J (K) is determined according to the following formula:
wherein, k= { K1, K2, … …, km }, K is the motion space parameter, f1, f2 and f3 are the first weight coefficient, the second weight coefficient and the third weight coefficient respectively, and T is the total number of sampling moments.
Optionally, the image information is information obtained by fusing a plurality of image data acquired from different angles.
In particular, the embodiment of the invention also provides a device for correcting the defect precision of the composite metal foil, which comprises a processor and a memory, wherein the memory stores a program, and the program is loaded and executed by the processor to realize the method for correcting the defect detection precision of the composite metal foil.
In particular, the embodiment of the invention also provides a defect detection system for the composite metal foil, which comprises the following steps:
a tensioning and carrying mechanism for continuously conveying the composite metal foil, wherein the tensioning and carrying mechanism comprises a tension roller for tensioning the composite metal foil and enabling the composite metal foil to have a preset tensioning force;
the vision system is arranged above the preset position and is used for collecting image information of a preset area of the composite metal foil;
the first height detection device is used for collecting the height value of the tension roller;
the second height detection device is used for collecting the height difference of the preset area on two sides of the width direction of the composite metal foil; and
according to the composite metal foil defect precision correction device, the composite metal foil defect precision correction device is in communication connection with the image acquisition device, the first height detection device and the second height detection device.
Optionally, the vision system comprises a plurality of line scan cameras, each of the pre-scan cameras being arranged at a different angle for acquiring image data of the preset area from a different angle.
According to a first aspect of the present invention, there is provided a method for correcting defect detection accuracy of a composite metal foil based on a vision system, which considers the influence of flatness of a detection area (i.e., the above-mentioned preset area) when constructing an objective function of a preset learning model, that is, a shape represented by a height value of a tension roller and a height difference of the preset area on both sides of a width direction of the composite metal foil is adapted to a reward function item, so that the preset learning model can be adapted to flatness of different detection areas, that is, a defect detection method which can be corrected according to flatness of the composite metal foil is provided, so that the obtained defect parameter is a more accurate parameter related to flatness of the current composite metal foil, thereby providing accuracy of defect detection.
Further, since the height value of the tension roller affects the angle change of the detection area in the length direction of the composite metal foil, the height difference in the width direction of the preset area directly reflects the angle change of the detection area in the width direction, the bending degree of the detection area can be expressed basically through the intervention of the two values, and the above-mentioned height value and the height difference are all easily measured parameters, so that the deformation degree of the detection area of the composite metal foil can be obtained conveniently through simple measurement.
According to the second aspect of the invention, the square root term in the shape adaptive reward function term represents the sensitivity to the height of the tension roller, the higher the sensitivity is, the more the corresponding reward is, the larger the height difference is, the more the exponential decay term is, and the decay speed can be controlled through setting the decay parameter, so that the shape adaptive reward function term can enable the final preset learning model to better match the deformation degree of various detection areas.
Further, the importance degree of different influencing factors can be flexibly adjusted by giving different weight coefficients to the accuracy reward function item, the false alarm penalty function item and the shape adaptation reward function item.
According to the third aspect of the present invention, the image information is obtained by fusing the image data acquired at a plurality of angles, that is, the multi-view stereoscopic vision technology is adopted, so that more accurate defect data can be obtained, and the defect depth of the composite metal foil can be calculated by comparing the parallaxes between the image data, thereby obtaining more accurate and more defect information.
Drawings
FIG. 1 is a flow chart of a method for correcting defect detection accuracy of a composite metal foil according to one embodiment of the invention;
FIG. 2 is a connection block diagram of a composite metal foil defect detection system according to one embodiment of the invention.
Detailed Description
In order to make the above objects, features and advantages of the present application more comprehensible, embodiments accompanied with figures are described in detail below. It is to be understood that the specific embodiments described herein are for purposes of illustration only and are not limiting. It should be further noted that, for convenience of description, only some, but not all of the structures related to the present application are shown in the drawings. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
The terms "comprising" and "having" and any variations thereof herein are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the present application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
In the defect detection process of the metal foil, the metal foil needs to be kept at a certain tension so as not to generate wrinkles, and the defect detection accuracy is prevented from being reduced due to the fact that the wrinkles are mistaken as defects. The inventor found in practice that as the detection time increases, tension rollers of the same height may generate different tension forces, for example, the tension roller height that can originally keep the metal foil at a proper tension force may decrease with the increase of time, in which case the height of the tension roller needs to be readjusted, and the change of the height of the tension roller may affect the flatness of the detection area of the metal foil, and thus the detection accuracy may be affected. Although such a change in height may have little effect on the flatness of the detection area, since the defect itself on the metal foil is a very minute structure, a decrease in defect detection accuracy due to a change in the height of the tension roller is still a non-negligible problem. In view of this, the present application provides the following solutions.
The embodiment provides a composite metal foil defect detection system, which comprises a discharging area, a detection area and a receiving area which are sequentially arranged. The discharging area can be provided with a discharging air expansion shaft and a first release film air expansion shaft, the detecting area is provided with a vision system, an adsorption roller and a tension roller, and the receiving area is provided with a receiving air expansion shaft and a second release film air expansion shaft. The vision system is used for collecting image information of a preset area of the composite metal foil. The discharging air expansion shaft is used for winding the composite metal foil to be detected, the composite metal foil is sequentially conveyed between the absorbing roller and the tension roller from the position between the discharging air expansion shaft and the first release film air expansion shaft, then conveyed between the receiving air expansion shaft and the second release film air expansion shaft, and the composite metal foil after being wound and detected by the second release film air expansion shaft, so that a continuous conveying and detecting state is formed. The tension roller adjusts the tension of the composite metal foil by changing the height thereof.
Fig. 1 is a flowchart of a method for correcting defect detection accuracy of a composite metal foil according to an embodiment of the present invention. In one embodiment, the composite metal foil is tensioned by a tension roller during detection, so that the composite metal foil has a preset tensioning force, and a vision system is arranged above a preset position of the composite metal foil and is used for acquiring image information of a preset area of the composite metal foil. As shown in fig. 1, the method for correcting defect detection accuracy of a composite metal foil according to the present embodiment includes:
step S100, acquiring image information of a preset area, a height value of a tension roller and a height difference of the preset area at two sides of the width direction of the composite metal foil;
step S200, constructing an accuracy rewarding function item and a false alarm punishment function item according to the image information;
step S300, constructing a shape adaptive reward function item according to the height value and the height difference;
step S400, establishing an objective function according to the accuracy rewarding function item, the false alarm punishment function item and the shape adaptation rewarding function item;
step S500, training a preset learning model by taking an optimization objective function as a target to obtain action space parameters of the preset learning model, wherein the output of the preset learning model is defect parameters of the composite metal foil;
step S600, corresponding target action space parameters are determined according to the current height value and the height difference;
step S700, obtaining the current defect parameters of the composite metal foil according to a preset learning model corresponding to the target action space parameters.
In step S100, the height value of the tension roller may be acquired by the first height detecting device, and the height difference of the preset area on both sides of the width direction of the composite metal foil may be acquired by the second height detecting device, where the height value may be replaced by the height change value.
The motion space parameters in step S500 are multiple sets of parameters, that is, parameters that can be dynamically adjusted during learning, and each set of parameters should be parameters related to the height value and the height difference, and each set of parameters corresponding to each height value and the height difference can be obtained through learning training. The target motion space parameters in step S600 are a set of parameters of the motion space parameters described above. The defect parameter in step S500 may be a defect size or a defect position, and the defect size may be a depth or a surface maximum size of the defect, or the like.
The embodiment provides a method for correcting defect detection precision of a composite metal foil based on a vision system, which considers the influence of flatness of a detection area (namely the preset area) when constructing an objective function of a preset learning model, namely, a shape represented by a height value of a tension roller and height differences of the preset area at two sides of the width direction of the composite metal foil is adapted to a reward function item, so that the preset learning model can adapt to flatness of different detection areas, namely, a defect detection method capable of correcting according to flatness of the composite metal foil is provided, and the obtained defect parameter is a more accurate parameter related to the flatness of the current composite metal foil, so that defect detection precision is provided.
Further, since the height value of the tension roller affects the angle change of the detection area in the length direction of the composite metal foil, the height difference in the width direction of the preset area directly reflects the angle change of the detection area in the width direction, the bending degree of the detection area can be expressed basically through the intervention of the two values, and the above-mentioned height value and the height difference are all easily measured parameters, so that the deformation degree of the detection area of the composite metal foil can be obtained conveniently through simple measurement.
In one embodiment, the accuracy bonus function term a (t) in step S200 is determined according to the following equation (1):
a(t)＝TP(t)+TN(t) (1)
wherein TP (t) represents the first sample number of the true defects in the defect samples detected at the moment t, and TN (t) represents the second sample number of the true normal surfaces in the normal surface samples detected at the moment t;
the false alarm penalty function term FP (t) in step S200 is a third sample number indicating that the detected defect sample at time t is not a real defect;
the shape-adaptive bonus function term c (t) in step S300 is determined according to the following formula (2):
wherein t represents time, h1 (t) represents a height value at time t, h2 (t) represents a height difference at time t, e is a natural constant, and a is an attenuation coefficient;
the objective function J (K) in step S400 is determined according to the following formula (3):
wherein, k= { K1, K2, … …, km }, K is an action space parameter, f1, f2 and f3 are a first weight coefficient, a second weight coefficient and a third weight coefficient respectively, and T is the total number of sampling moments.
The attenuation coefficient a, the first weight coefficient f1, the second weight coefficient f2 and the third weight coefficient f3 in the formula can be set by themselves, or can be set specifically by examining the accuracy condition after continuously adjusting the values. The number of motion space parameters may also be set according to computational power or accuracy requirements.
In this embodiment, the square root term in the shape adaptive reward function term represents the sensitivity to the height of the tension roller, the higher the sensitivity is, the more the corresponding reward is, the greater the height difference is, the more the exponential decay term is, and the decay speed can be controlled by setting the decay parameter, so that the shape adaptive reward function term can enable the final preset learning model to better match the deformation degree of various detection areas.
Further, the importance degree of different influencing factors can be flexibly adjusted by giving different weight coefficients to the accuracy reward function item, the false alarm penalty function item and the shape adaptation reward function item.
In one embodiment, the image information is obtained by fusing a plurality of image data acquired from different angles. For example by arranging a central camera directly above the predetermined area, two edge cameras directed into the predetermined area are arranged on both sides of the symmetry of the central camera.
The image information in this embodiment is information obtained by fusing image data acquired at a plurality of angles, that is, a multi-view stereoscopic vision technology is adopted, so that more accurate defect data may be obtained, and the defect depth of the composite metal foil may be calculated by comparing disparities between the image data, thereby obtaining more accurate and more defect information.
The invention also provides a device for correcting the defect precision of the composite metal foil, which comprises a processor and a memory, wherein the memory stores a program, and the program is loaded and executed by the processor to realize the method for correcting the defect detection precision of the composite metal foil according to any embodiment.
FIG. 2 is a block diagram of a connection of a composite metal foil defect detection system 100 according to one embodiment of the invention. As shown in fig. 2, the present invention further provides a system 100 for detecting defects of a composite metal foil, which includes a tensioning and carrying mechanism (not shown), a vision system 10, a first height detecting device 20, a second height detecting device 30, and a device 40 for correcting defects of a composite metal foil according to the above embodiment. The tensioning and carrying mechanism is used for continuously conveying the composite metal foil and comprises a tension roller, wherein the tension roller is used for tensioning the composite metal foil and enabling the composite metal foil to have a preset tensioning force. The vision system 10 is disposed above a predetermined position for acquiring image information of a predetermined area of the composite metal foil. The first height detection device 20 is used for collecting the height value of the tension roller. The second height detecting device 30 is used for collecting the height difference of the preset area at two sides of the width direction of the composite metal foil. The composite metal foil defect precision correction device 40 is in communication connection with the image acquisition device, the first height detection device 20 and the second height detection device 30. In one embodiment, vision system 10 includes a plurality of line scan cameras, each of which is arranged at a different angle for acquiring image data of a predetermined area from a different angle.
The defect precision correction device 40 for composite metal foil according to the present embodiment considers the influence of flatness of the detection area (i.e. the above-mentioned preset area) when constructing the objective function of the preset learning model, that is, the shape represented by the height value of the tension roller and the height difference of the preset area at both sides of the width direction of the composite metal foil is adapted to the reward function term, so that the preset learning model can adapt to the flatness of different detection areas, that is, a defect detection method capable of correcting according to the flatness of the composite metal foil is provided, so that the obtained defect parameter is a more accurate parameter related to the flatness of the current composite metal foil, thereby providing the precision of defect detection.
Further, since the height value of the tension roller affects the angle change of the detection area in the length direction of the composite metal foil, the height difference in the width direction of the preset area directly reflects the angle change of the detection area in the width direction, the bending degree of the detection area can be expressed basically through the intervention of the two values, and the above-mentioned height value and the height difference are all easily measured parameters, so that the deformation degree of the detection area of the composite metal foil can be obtained conveniently through simple measurement.
The above examples illustrate only a few embodiments of the invention, which are described in detail and are not to be construed as limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
Claims (10)
1. The utility model provides a correction method of composite metal foil defect detection precision, the composite metal foil is tensioning through tension cylinder when detecting to make the composite metal foil have preset tensioning force, the vision system is arranged to the top of the preset position of composite metal foil for gather the image information of the preset region of composite metal foil, its characterized in that, the method includes:
acquiring image information of the preset area, a height value of the tension roller and a height difference of the preset area at two sides of the composite metal foil in the width direction;
constructing an accuracy rewarding function item and a false alarm punishment function item according to the image information;
constructing a shape-adaptive reward function term according to the height value and the height difference;
establishing an objective function according to the accuracy rewarding function item, the false alarm punishment function item and the shape adaptation rewarding function item;
training a preset learning model by taking the optimization of the objective function as a target to obtain action space parameters of the preset learning model, wherein the output of the preset learning model is a defect parameter of the composite metal foil;
determining corresponding target action space parameters according to the current height value and the height difference;
and obtaining the current defect parameters of the composite metal foil according to the preset learning model corresponding to the target action space parameters.
2. The method for correcting defect detection accuracy of composite metal foil according to claim 1, wherein the defect parameter is a defect size or a defect position.
3. The method for correcting a defect detection accuracy of a composite metal foil according to claim 1, wherein the shape-adaptive bonus function term c (t) in the step of constructing a shape-adaptive bonus function term from the height value and the height difference is determined according to the following formula:
where t represents time, h1 (t) represents the height value at time t, h2 (t) represents the height difference at time t, e is a natural constant, and a is an attenuation coefficient.
4. A method for correcting defect detection accuracy of composite metal foil according to claim 3, wherein in the step of constructing an accuracy rewards function term and a false positive penalty function term from the image information, the accuracy rewards function term a (t) is determined according to the following formula:
a(t)＝TP(t)+TN(t)；
wherein TP (t) represents the first sample number of the true defects in the defect samples detected at the time t, and TN (t) represents the second sample number of the true normal surfaces in the normal surface samples detected at the time t.
5. The method according to claim 4, wherein in the step of constructing an accuracy rewarding function term and a false alarm penalty function term according to the image information, the false alarm penalty function term FP (t) is a third sample number indicating that the detected defect sample at time t is not a true defect.
6. The method according to claim 5, wherein in the step of creating an objective function from the accuracy bonus function term, the false alarm penalty function term, and the shape adaptive bonus function term, the objective function J (K) is determined according to the following formula:
wherein, k= { K1, K2, … …, km }, K is the motion space parameter, f1, f2 and f3 are the first weight coefficient, the second weight coefficient and the third weight coefficient respectively, and T is the total number of sampling moments.
7. The method for correcting defect detection accuracy of composite metal foil according to any one of claims 1 to 6, wherein the image information is information obtained by fusing a plurality of image data acquired from different angles.
8. A composite metal foil defect accuracy correction apparatus comprising a processor and a memory, the memory having stored therein a program that is loaded and executed by the processor to implement the composite metal foil defect detection accuracy correction method of any one of claims 1-7.
9. A composite metal foil defect detection system, comprising:
a tensioning and carrying mechanism for continuously conveying the composite metal foil, wherein the tensioning and carrying mechanism comprises a tension roller for tensioning the composite metal foil and enabling the composite metal foil to have a preset tensioning force;
the vision system is arranged above the preset position and is used for collecting image information of a preset area of the composite metal foil;
the first height detection device is used for collecting the height value of the tension roller;
the second height detection device is used for collecting the height difference of the preset area on two sides of the width direction of the composite metal foil; and
the composite metal foil defect accuracy correction device of claim 8, wherein the composite metal foil defect accuracy correction device is communicatively coupled to the image acquisition device, the first height detection device, and the second height detection device.
10. The composite metal foil defect detection system of claim 9, wherein the vision system comprises a plurality of line scan cameras, each of the pre-scan cameras being arranged at a different angle for acquiring image data of the pre-set area from a different angle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410097545.2A CN117893885A (en) | 2024-01-24 | 2024-01-24 | Method, device and system for correcting defect detection precision of composite metal foil |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410097545.2A CN117893885A (en) | 2024-01-24 | 2024-01-24 | Method, device and system for correcting defect detection precision of composite metal foil |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117893885A true CN117893885A (en) | 2024-04-16 |
Family
ID=90647343
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410097545.2A Pending CN117893885A (en) | 2024-01-24 | 2024-01-24 | Method, device and system for correcting defect detection precision of composite metal foil |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117893885A (en) |
-
2024
- 2024-01-24 CN CN202410097545.2A patent/CN117893885A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR100465862B1 (en) | Method for measuring quality of bandlike body method for suppressing camber instrument for measuring quality of bandlike body rolling machine and triming device | |
| CN101815665A (en) | Accurate tracking of web features through converting processes | |
| WO2010143953A1 (en) | Method for determining weights of eggs, and apparatus | |
| JP2006189315A (en) | Optical shape measurement method | |
| CN109059789B (en) | Cable pitch online detection method based on machine vision | |
| CN116630327B (en) | Boiler state abnormity monitoring system based on thermodynamic diagram | |
| CN107421438A (en) | Film size detection control system and its method based on machine vision | |
| CN117893885A (en) | Method, device and system for correcting defect detection precision of composite metal foil | |
| US5193398A (en) | Measuring method for determining the elongation after rupture of a tensile testpiece | |
| JP4705277B2 (en) | Oil amount distribution measuring device and oil amount distribution measuring method | |
| US10024775B2 (en) | Method and device for determining the abrasion properties of a coated flat product | |
| JP4854602B2 (en) | Method for detecting the shape of rolled material | |
| EP1668316B1 (en) | Sheet-surface analyser and method of analysing a sheet-surface | |
| CN110243292A (en) | Splitting system and cutting detection method | |
| CN116205894A (en) | Bearing roller defect detection method based on multi-information fusion | |
| KR101406648B1 (en) | System and method for measuring strip deviation | |
| CA2598921C (en) | Method of and apparatus for manufacturing a metal strip | |
| JPH1194767A (en) | Method and apparatus for inspecting formation | |
| CN103154709A (en) | Sheet-material inspection method and sheet-material inspection device | |
| JP3716650B2 (en) | Surface flaw inspection device | |
| CN117110306A (en) | Lithium battery coating detection system and method | |
| KR100605708B1 (en) | Apparatus for measuring temperature of strip in twin roll strip casting process | |
| JP7447874B2 (en) | Method for generating a model for estimating the amount of meandering in a steel plate, method for estimating the amount of meandering in a steel plate, method for controlling meandering in a steel plate, and method for manufacturing a steel plate | |
| JP2020041841A (en) | Change rate estimating apparatus, change rate estimating method, state estimating device, and state estimating method | |
| JP6470293B2 (en) | Method and apparatus for measuring wear characteristics of galvanyl flat steel products |
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 |