CN107578168B - Method and device for defect library transplantation and electronic equipment - Google Patents
Method and device for defect library transplantation and electronic equipment Download PDFInfo
- Publication number
- CN107578168B CN107578168B CN201710789596.1A CN201710789596A CN107578168B CN 107578168 B CN107578168 B CN 107578168B CN 201710789596 A CN201710789596 A CN 201710789596A CN 107578168 B CN107578168 B CN 107578168B
- Authority
- CN
- China
- Prior art keywords
- target
- target system
- information
- source system
- standard
- 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.)
- Active
Links
Images
Abstract
The invention discloses a method and a device for defect bank transplantation and electronic equipment, and relates to the technical field of surface quality detection of cold-rolled sheet strips, wherein the method comprises the following steps: acquiring basic identification information of a target system; comparing the basic identification information with standard identification information of a source system, and judging whether the target system is matched with the source system; if so, acquiring the type information of the target product of the target system; comparing the target product type information with the standard product type information of the source system, and judging whether the target product type information is matched with the standard product type information; and if so, transplanting the defect library of the source system to the target system. The method, the device and the electronic equipment for transplanting the defect library achieve the technical effect of quickly transplanting the defect library of the detection equipment to different target systems.
Description
Technical Field
The invention belongs to the technical field of surface quality detection of cold-rolled sheet strips, and particularly relates to a method and a device for defect bank transplantation and electronic equipment.
Background
The surface quality of the plate strip steel becomes an important evaluation index of the cold-rolled plate strip steel, and surface detection systems in various cold-rolled plate strip surface defect detection equipment become standard configurations of cold-rolled strip steel production enterprises. The length of the preparation period of the detection equipment is a bottleneck restricting the production and sale processes of high-quality cold-rolled strip steel products, and restricts the development of various steel enterprises to a great extent.
The surface quality detection system is a visual online automatic detection system for detecting the surface defects of the strip steel, can automatically detect the surface defects of the strip steel, accurately name the defects, provide alarm information for a user, and improve the efficiency and quality of quality inspection work. The establishment of the surface detection system defect library is the basis for the effective and accurate operation of the system and is also a key link in the starting process of the system.
However, in the prior art, due to the situation that the target system and the source system are not adaptive, the technical defect that the defect library of the detection device cannot be rapidly migrated to different target systems is caused.
Disclosure of Invention
The invention aims to solve the technical problem that the defect library of the detection equipment cannot be rapidly transplanted to different target systems.
To solve the above technical problem, according to an aspect of the present invention, there is provided a method for defect bank migration, including: acquiring basic identification information of a target system; comparing the basic identification information with standard identification information of a source system, and judging whether the target system is matched with the source system; if so, acquiring the type information of the target product of the target system; comparing the target product type information with the standard product type information of the source system, and judging whether the target product type information is matched with the standard product type information; and if so, transplanting the defect library of the source system to the target system.
Further, after comparing the basic identification information with the standard identification information of the source system and determining whether the target system and the source system are matched, the method further includes: if not, the migration is ended.
Further, after comparing the target product type information with the standard product type information of the source system and determining whether the target product type information and the standard product type information are suitable, the method further includes: if not, correcting the defect sample in the defect library in the source system; and transplanting the corrected defect library to the target system.
Further, the basic identification information includes: basic material information and basic production process information; the standard identification information includes: standard material information and standard production process information; comparing the basic identification information with standard identification information of a source system, and judging whether the target system is matched with the source system comprises: comparing the basic material information with the standard material information, and comparing the basic production process information with the standard production process information; and if the basic material information is the same as the standard material information and the basic production process information is the same as the standard production process information, matching the target system with the source system.
Further, the comparing the basic material information with the standard material information, and the basic production process information with the standard production process information respectively includes: and if the basic material information is different from the standard material information and/or the basic production process information is different from the standard production process information, the target system is not matched with the source system.
Further, after the migrating the defect library of the source system to the target system, the method further comprises: importing the detection rule of the source system into the target system; comparing the defect name of the defect sample of the defect library with the defect directory of the target system, and judging whether the detection rule is adaptive to the target system; and if so, performing local self-learning on the target system.
Further, the comparing the defect name of the defect sample of the defect library with the defect list of the target system, and determining whether the detection rule and the target system are suitable includes: and if not, modifying the rule content of the detection rule, and after the rule content is matched with the target system, locally self-learning the target system.
Further, after the local self-learning of the target system, the method further includes: obtaining a learning score A after local learning; the learning achievement A and a preset first expected target Y of the target system are compared1And a second desired target Y2Carrying out comparison; wherein, the Y is2Less than or equal to Y1(ii) a If A > Y1Then the migration is ended.
Further, the learning achievement A and a preset first expected goal Y of the goal system are combined1And a second desired target Y2The comparison includes: if A is less than or equal to Y2Adjusting the defect classification of the target system such that A > Y1After that, the migration is ended.
Further, said Y is1The value ranges are as follows: y is more than or equal to 65%1Less than or equal to 95 percent; said Y is2The value ranges are as follows: y is more than or equal to 65%2≤95％。
According to yet another aspect of the present invention, there is also provided an apparatus for defect bank migration, the apparatus comprising:
the basic identification acquisition module is used for acquiring basic identification information of the target system; the matching judgment module is used for comparing the basic identification information with standard identification information of a source system and judging whether the target system is matched with the source system; the product type information acquisition module is used for acquiring the target product type information of the target system if the matching is performed; the adaptability judging module is used for comparing the target product type information with the standard product type information of the source system and judging whether the target product type information is adaptive to the standard product type information; and the transplantation defect library module is used for transplanting the defect library of the source system to the target system if the source system is adaptive to the target system.
Further, the judgment adaptability module is further configured to: if not, correcting the defect sample in the defect library in the source system; and transplanting the corrected defect library to the target system.
According to yet another aspect of the present invention, the present invention also provides an electronic device for defect bank migration, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the program:
acquiring basic identification information of a target system; comparing the basic identification information with standard identification information of a source system, and judging whether the target system is matched with the source system; if so, acquiring the type information of the target product of the target system; comparing the target product type information with the standard product type information of the source system, and judging whether the target product type information is matched with the standard product type information; and if so, transplanting the defect library of the source system to the target system.
According to yet another aspect of the present invention, the present invention also provides a computer readable storage medium for defect library migration, having stored thereon a computer program which, when executed by a processor, performs the steps of:
acquiring basic identification information of a target system; comparing the basic identification information with standard identification information of a source system, and judging whether the target system is matched with the source system; if so, acquiring the type information of the target product of the target system; comparing the target product type information with the standard product type information of the source system, and judging whether the target product type information is matched with the standard product type information; and if so, transplanting the defect library of the source system to the target system.
Has the advantages that:
the invention provides a method, a device and electronic equipment for defect library transplantation, wherein after the acquired basic identification information of a target system is compared with the standard identification information of a source system, the target system is matched with the source system, namely the target system can be used for transplanting a defect library to the source system. Therefore, the target product type information and the standard product type information of the source system are continuously compared, and if the target product type information and the standard product type information are adaptive, the defect library in the source system can be transplanted into the target system. The target system can be applied to the source system firstly, then the defect library in the source system can be transplanted in the target system, and finally the defect library in the source system is transplanted to the target system. Therefore, whether the source system is adaptive to the target system can be judged in time in different target systems, and the defect library in the source system can be transplanted into the target system in time when the target system is adaptive to the source system, so that the technical effect of quickly transplanting the defect library of the detection equipment into different target systems is achieved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a diagram illustrating a method for defect library migration according to an embodiment of the present invention;
FIG. 2 is a diagram illustrating an apparatus for defect library migration according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of an electronic device for defect library migration according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a computer-readable storage medium for defect library migration according to an embodiment of the present invention.
Detailed Description
The invention provides a method, a device and electronic equipment for defect library transplantation, wherein after the acquired basic identification information of a target system is compared with the standard identification information of a source system, the target system is matched with the source system, namely the target system can be used for transplanting a defect library to the source system. Therefore, the target product type information and the standard product type information of the source system are continuously compared, and if the target product type information and the standard product type information are adaptive, the defect library in the source system can be transplanted into the target system. The target system can be applied to the source system firstly, then the defect library in the source system can be transplanted in the target system, and finally the defect library in the source system is transplanted to the target system. Therefore, whether the source system is adaptive to the target system can be judged in time in different target systems, and the defect library in the source system can be transplanted into the target system in time when the target system is adaptive to the source system, so that the technical effect of quickly transplanting the defect library of the detection equipment into different target systems is achieved.
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present invention belong to the protection scope of the present invention; the "and/or" keyword referred to in this embodiment represents sum or two cases, in other words, a and/or B mentioned in the embodiment of the present invention represents two cases of a and B, A or B, and describes three states where a and B exist, such as a and/or B, which represents: only A does not include B; only B does not include A; including A and B.
Example one
Referring to fig. 1, a method for defect library migration according to an embodiment of the present invention includes:
step S110, basic identification information of the target system is obtained. The basic identification information includes: basic material information and basic production process information.
Specifically, the target system is a plate strip steel surface detection system which needs to be implanted into a defect library in a production enterprise.
The basic material information is: the material of the detection object of the target system.
The basic production process information is: and (3) a production process of the detection object of the target system.
The basic material information and the basic production process information of the target system can be collected simultaneously, and the material information of the detection object of the target system and the production process information of the detection object of the target system are collected in real time through various sensors and the like.
Step S120, comparing the basic identification information with the standard identification information of the source system, and judging whether the target system is matched with the source system. If not, the migration is ended. If so, the process proceeds to step S130. Wherein the standard identification information includes: standard material information and standard production process information.
Comparing the basic identification information with the standard identification information of the source system, namely: and comparing the basic material information with the standard material information, and comparing the basic production process information with the standard production process information respectively. And if the basic material information is the same as the standard material information and the basic production process information is the same as the standard production process information, matching the target system with the source system. And if the basic material information is different from the standard material information and/or the basic production process information is different from the standard production process information, the target system is not matched with the source system.
Specifically, the source system can implant the defect library to be migrated into the target system, and the source system has the defect library.
The standard material information is: the material of the detection object of the source system.
The standard production process information refers to: the production process of the detection object of the source system.
Standard material information and standard production process information are prestored in the source system. Namely, the material information of the detection object of the source system and the production process information of the detection object of the source system are stored in the source system before the defect library transplantation is carried out.
For a more detailed explanation, the base identification information is compared with the standard identification information of the source system, and after comparison, two cases will occur, namely, the target system and the source system are matched, or the target system and the source system are not matched. Two embodiments are now provided for the following detailed description:
in a first embodiment, the target system and the source system are matched after comparing the basic identification information with the standard identification information of the source system. And comparing the basic material information with the standard material information and comparing the basic production process information with the standard production process information respectively to judge whether the target system is matched with the source system.
And matching the target system with the source system when the basic material information of the target system is the same as the standard material information of the source system and the basic production process information of the target system is the same as the standard production process information of the source system. At this time, after comparing the basic identification information with the standard identification information of the source system, it can be determined that the detection object of the target system and the detection object of the source system both have the same material, similar or same production process, so that the condition for using the source system to transplant in the target system is provided, thereby achieving the technical effect of feeding back to the user that the source system can be used to transplant the defect library to the target system.
In a second embodiment, the target system and the source system are not matched after comparing the basic identification information with the standard identification information of the source system. And comparing the basic material information with the standard material information and comparing the basic production process information with the standard production process information respectively to judge whether the target system is matched with the source system.
And when the basic material information is different from the standard material information and/or the basic production process information is different from the standard production process information, the target system is not matched with the source system. Namely, the first case: when the basic material information is different from the standard material information and the basic production process information is different from the standard production process information; in the second case: and when the basic material information is different from the standard material information, or the basic production process information is different from the standard production process information. When either of these two conditions occurs, then the target system and the source system do not match. When the target system and the source system do not match, the migration of the defect library to the target system may be terminated. In addition, at this time, it can be determined that the detection object of the target system and the detection object of the source system do not have the same material, similar or the same production process, and therefore, the condition for using the source system to perform migration in the target system is not provided, so that the technical effect of being able to feed back to the user that the source system cannot be used to perform migration of the defect library to the target system is achieved.
And step S130, if the target product type information is matched with the target product type information, acquiring the target product type information of the target system.
Specifically, the target product type information of the target system may be: the target system detects the type of object. The type information of the product detected by the target system can be collected in real time through various sensors and the like.
Step S140, comparing the type information of the target product with the type information of the standard product of the source system, and judging whether the type information of the target product is suitable for the type information of the standard product.
Specifically, the standard product type information of the source system is: the source system detects type information of the object. The standard product type information may be stored in the source system in advance, that is, before the defect library migration is performed, the standard product type information is stored in the source system.
Comparing the target product type information with the standard product type information of the source system, namely: and comparing the target product type information of the target system with the standard product type information of the source system. Judging whether the target product type information and the standard product type information are suitable by judging whether the target product type information of the target system is the same as the standard product type information of the source system.
And if the target product type information of the target system is the same as the standard product type information of the source system, the target product type information is adaptive to the standard product type information. And if the target product type information of the target system is different from the standard product type information of the source system, the target product type information and the standard product type information are not suitable.
And step S150, if the defect library is suitable, transplanting the defect library of the source system to the target system. If not, correcting the defect sample in the defect library in the source system; and transplanting the corrected defect library to the target system.
After the defect library of the source system is transplanted to the target system, the detection rule of the source system is imported into the target system, and the defect name of the defect sample of the defect library is compared with the defect directory of the target system to judge whether the detection rule and the target system are adaptive.
If the detection rule is adaptive to the target system, locally self-learning the target system; and if the detection rule is not adaptive to the target system, modifying the rule content of the detection rule, and after the rule content is matched with the target system, the target system carries out local self-learning.
After the target system carries out local self-learning, the learning achievement A and a preset first expected target Y of the target system are compared1And a second desired target Y2And (6) carrying out comparison.
After comparison, if A > Y1Then the transplantation is finished; if A is less than or equal to Y2Adjusting the defect classification of the target system such that A > Y1After that, the migration is ended. Wherein, the Y is2Less than or equal to Y1Said Y is1The value ranges are as follows: y is more than or equal to 65%1Less than or equal to 95 percent, Y2The value ranges are as follows: y is more than or equal to 65%2Less than or equal to 95 percent, and the learning achievement A after the local learning is assumed to be obtained.
Specifically, the determination as to whether the target product type information and the standard product type information are suitable is performed in step S140. If the judgment result is that: and if the type information of the standard product is matched with the type information of the standard product, transplanting the defect library of the source system into the target system.
If the result of the determination in step S140 is: and if the standard product type information and the standard product type information do not adapt to each other, correcting the defect sample in the defect library in the source system, and transplanting the corrected defect library to the target system by correcting the defect sample.
And after the defect library of the source system is transplanted to the target system, importing the detection rule of the source system into the target system. And comparing the defect name of the defect sample of the defect library with the defect directory of the target system to judge whether the detection rule transplanted into the target system is suitable for the target system. Namely, whether the detection rule can be applied in the target system is judged after the detection rule is transplanted to the target system. At this time, two situations will occur, that is, the detection rule in the target system is adaptive to the target system, and the detection rule in the target system is not applicable to the target system, and two embodiments are now provided for the following explanation:
in a first embodiment, if the defect name of the defect sample of the defect library is in the defect directory of the target system, the detection rule migrated to the target system is adaptive to the target system. At this time, the target system starts local self-learning, that is, self-learning of the target system.
In a second embodiment, if the defect name of the defect sample of the defect library is not in the defect directory of the target system, the detection rule migrated to the target system and the target system are not applicable. At this time, the rule content of the rule is detected by modifying and transplanting the rule into the target system, and after the rule content is matched with the target system, the target system starts local self-learning, namely the target system is self-learned.
In the two embodiments, after the target system starts local self-learning, the learning achievement a and a preset first expected target Y of the target system are combined1And a second desired target Y2And (6) carrying out comparison. Namely the learning achievement A and a preset first expected target Y of the target system1And a second desired target Y2Are compared separately, and Y is2Less than or equal to Y1。
Y1The value ranges are as follows:65％≤Y1less than or equal to 95 percent. When Y is1If the ratio is less than 65%, the self-learning accuracy of the target system is reflected to be low, and at the moment, the establishment of the target system defect library loses the self-action and the target cannot be subjected to defect detection. When Y is195%, in a real production line, the 95% accuracy has reached the limit of the target system accuracy.
Y2The value ranges are as follows: y is more than or equal to 65%2Less than or equal to 95 percent. When Y is2If the ratio is less than 65%, the self-learning accuracy of the target system is reflected to be low, and at the moment, the establishment of the target system defect library loses the self-action and the target cannot be subjected to defect detection. When Y is295%, in a real production line, the 95% accuracy has reached the limit of the target system accuracy.
The first expected target Y1And a second desired target Y2May be stored in advance in the target system or the source system. Y is1And Y2The values of (a) can be different, but need to be in accordance with: y is2≤Y1。
For the above A and Y1、Y2For a more detailed explanation of the comparison, respectively, two embodiments are now provided for the following detailed description:
in a first embodiment, when A > Y1The learning result A is larger than the first expected target Y1This indicates that the accuracy of the self-learning of the target system reaches the first expected target, and at this time, the migration of the defect library to the target system may be finished. By locally self-learning the target system, the defect samples and the detection rules of the defect library transplanted into the target system can be organically combined with the target system. Therefore, the target system after the defect library transplantation has the technical effect of higher stability.
In a second embodiment, when A ≦ Y2By adjusting the defect classification of the target system, A can be made to A > Y1And then, finishing the transplantation of the defect library to the target system. A is less than or equal to Y2The accuracy rate reflecting the self-learning of the target system does not reach the second expected purposeThe accuracy of the target, i.e. self-learning, is low. And enabling the target system to enter self-learning again by adjusting the defect classification of the target system until the self-learning achievement A of the target system meets the following requirements: a > Y1When it is determined that the learning achievement A is larger than the first expected goal Y1This reflects that the self-learning accuracy of the target system reaches the first expected target, and at this time, the migration of the defect library to the target system may be terminated. By locally self-learning the target system, the defect samples and the detection rules of the defect library transplanted into the target system can be organically combined with the target system. Therefore, the target system after the defect library transplantation has the technical effect of higher stability.
The invention provides a method for defect library transplantation, which is characterized in that after the acquired basic identification information of a target system is compared with the standard identification information of a source system, the target system is matched with the source system, namely the target system can be used for transplanting a defect library to the source system. Therefore, the target product type information and the standard product type information of the source system are continuously compared, and if the target product type information and the standard product type information are adaptive, the defect library in the source system can be transplanted into the target system. The target system can be applied to the source system firstly, then the defect library in the source system can be transplanted in the target system, and finally the defect library in the source system is transplanted to the target system. Therefore, whether the source system is adaptive to the target system can be judged in time in different target systems, and the defect library in the source system can be transplanted into the target system in time when the target system is adaptive to the source system, so that the technical effect of quickly transplanting the defect library of the detection equipment into different target systems is achieved.
Based on the same inventive concept, the present application provides an embodiment of an apparatus for defect library migration corresponding to the first embodiment, which is detailed in the second embodiment.
Example two
As shown in fig. 2, a second embodiment of the present invention provides an apparatus for defect library migration, where the apparatus includes:
a basic identifier obtaining module 210, configured to obtain basic identifier information of a target system;
a matching judgment module 220, configured to compare the basic identification information with standard identification information of a source system, and judge whether the target system and the source system are matched;
a product type information obtaining module 230, configured to, if matching, obtain target product type information of the target system;
a suitability judging module 240, configured to compare the target product type information with standard product type information of the source system, and judge whether the target product type information is suitable for the standard product type information;
wherein, the adaptive determining module 240 is further configured to: if not, correcting the defect sample in the defect library in the source system; and transplanting the corrected defect library to the target system.
And the transplantation defect library module 250 is used for transplanting the defect library of the source system to the target system if the defect library is adaptive to the target system.
The invention provides a device for defect library transplantation, wherein after the acquired basic identification information of a target system is compared with the standard identification information of a source system through a matching judgment module 220, the target system is matched with the source system, namely the target system can be used for transplanting a defect library to the source system. So, continuing with the determining adaptability module 240, the target product type information and the standard product type information of the source system are compared, and if the target product type information and the standard product type information are adaptive, the defect library in the source system can be migrated to the target system. The target system can be applied to the source system firstly, then the defect library in the source system can be transplanted in the target system, and finally the defect library in the source system is transplanted to the target system. Therefore, whether the source system is adaptive to the target system can be judged in time in different target systems, and the defect library in the source system can be transplanted into the target system in time when the target system is adaptive to the source system, so that the technical effect of quickly transplanting the defect library of the detection equipment into different target systems is achieved.
Based on the same inventive concept, the present application provides an embodiment of an electronic device for defect library migration corresponding to the first embodiment, which is detailed in the third embodiment.
EXAMPLE III
As shown in fig. 3, a third embodiment of the present invention provides an electronic device for defect library migration, which includes a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor 320, where the processor 320 executes the program to implement the following steps:
acquiring basic identification information of a target system;
comparing the basic identification information with standard identification information of a source system, and judging whether the target system is matched with the source system;
if so, acquiring the type information of the target product of the target system;
comparing the target product type information with the standard product type information of the source system, and judging whether the target product type information is matched with the standard product type information;
and if so, transplanting the defect library of the source system to the target system.
The invention provides an electronic device for defect library transplantation, wherein after the acquired basic identification information of a target system is compared with the standard identification information of a source system, the target system is matched with the source system, namely the target system can be used for transplanting a defect library to the source system. Therefore, the target product type information and the standard product type information of the source system are continuously compared, and if the target product type information and the standard product type information are adaptive, the defect library in the source system can be transplanted into the target system. The target system can be applied to the source system firstly, then the defect library in the source system can be transplanted in the target system, and finally the defect library in the source system is transplanted to the target system. Therefore, whether the source system is adaptive to the target system can be judged in time in different target systems, and the defect library in the source system can be transplanted into the target system in time when the target system is adaptive to the source system, so that the technical effect of quickly transplanting the defect library of the detection equipment into different target systems is achieved.
Based on the same inventive concept, the present application provides an embodiment of a computer-readable storage medium 400 for defect library migration corresponding to the first embodiment, which is described in detail in the fourth embodiment.
Example four
As shown in fig. 4, a fourth embodiment of the present invention provides a computer-readable storage medium 400 for defect library migration, on which a computer program 411 is stored, which when executed by a processor implements the following steps:
acquiring basic identification information of a target system;
comparing the basic identification information with standard identification information of a source system, and judging whether the target system is matched with the source system;
if so, acquiring the type information of the target product of the target system;
comparing the target product type information with the standard product type information of the source system, and judging whether the target product type information is matched with the standard product type information;
and if so, transplanting the defect library of the source system to the target system.
The present invention provides a computer readable storage medium 400 for defect library migration, wherein after comparing the obtained basic identification information of the target system with the standard identification information of the source system, the target system and the source system are matched, i.e. the target system can be used for the migration of the defect library to the source system. Therefore, the target product type information and the standard product type information of the source system are continuously compared, and if the target product type information and the standard product type information are adaptive, the defect library in the source system can be transplanted into the target system. The target system can be applied to the source system firstly, then the defect library in the source system can be transplanted in the target system, and finally the defect library in the source system is transplanted to the target system. Therefore, whether the source system is adaptive to the target system can be judged in time in different target systems, and the defect library in the source system can be transplanted into the target system in time when the target system is adaptive to the source system, so that the technical effect of quickly transplanting the defect library of the detection equipment into different target systems is achieved.
In the implementation process, when the computer program 411 is executed by a processor, any one of the first embodiment may be implemented.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program 411 products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (5)
1. A defect library transplanting method applied to a cold-rolled sheet strip surface quality detection system is characterized by comprising the following steps:
acquiring basic identification information of a target system;
comparing the basic identification information with standard identification information of a source system, and judging whether the target system is matched with the source system;
if so, acquiring the type information of the target product of the target system;
comparing the target product type information with the standard product type information of the source system, and judging whether the target product type information is matched with the standard product type information;
if so, transplanting the defect library of the source system to the target system;
the basic identification information includes: basic material information and basic production process information;
the standard identification information includes: standard material information and standard production process information;
comparing the basic identification information with standard identification information of a source system, and judging whether the target system is matched with the source system comprises:
comparing the basic material information with the standard material information, and comparing the basic production process information with the standard production process information;
and if the basic material information is the same as the standard material information and the basic production process information is the same as the standard production process information, matching the target system with the source system.
2. The method of claim 1, wherein after comparing the target product type information with standard product type information of the source system and determining whether the target product type information and the standard product type information are compatible, the method further comprises:
if not, correcting the defect sample in the defect library in the source system;
and transplanting the corrected defect library to the target system.
3. The method of claim 1, wherein after the migrating the defect library of the source system to the target system, the method further comprises:
importing the detection rule of the source system into the target system;
comparing the defect name of the defect sample of the defect library with the defect directory of the target system, and judging whether the detection rule is adaptive to the target system;
and if so, performing local self-learning on the target system.
4. The method of claim 3, wherein after locally self-learning the target system, further comprising:
obtaining a learning score A after local learning;
the learning achievement A and a preset first expected target Y of the target system are compared1And a second desired target Y2Carrying out comparison; wherein, the Y is2Less than or equal to Y1；
If A > Y1Then the migration is ended.
5. The method of claim 4, wherein said associating said learning achievement A with a predetermined first desired goal Y of said goal system1And a second desired target Y2The comparison includes:
if A is less than or equal to Y2Adjusting the defect classification of the target system such that A > Y1After that, the migration is ended.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710789596.1A CN107578168B (en) | 2017-09-05 | 2017-09-05 | Method and device for defect library transplantation and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710789596.1A CN107578168B (en) | 2017-09-05 | 2017-09-05 | Method and device for defect library transplantation and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107578168A CN107578168A (en) | 2018-01-12 |
| CN107578168B true CN107578168B (en) | 2020-12-29 |
Family
ID=61029819
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710789596.1A Active CN107578168B (en) | 2017-09-05 | 2017-09-05 | Method and device for defect library transplantation and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107578168B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108037739A (en) * | 2017-11-09 | 2018-05-15 | 广州兴森快捷电路科技有限公司 | The process management and control method and system of PCB product |
| CN113435759B (en) * | 2021-07-01 | 2023-07-04 | 贵州电网有限责任公司 | Primary equipment risk intelligent assessment method based on deep learning |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| NL6909260A (en) * | 1968-06-24 | 1969-12-30 | ||
| CN101288072B (en) * | 2005-08-30 | 2012-05-23 | 维特·F·利尔 | Transfer and conversion of data structure |
| CN102637258B (en) * | 2012-04-01 | 2014-05-28 | 首钢总公司 | Method for creating online surface quality detection system defect library |
-
2017
- 2017-09-05 CN CN201710789596.1A patent/CN107578168B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN107578168A (en) | 2018-01-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106097361B (en) | Defect area detection method and device | |
| JP4852890B2 (en) | Automatic cell pass / fail judgment system | |
| US10169861B2 (en) | Image processing apparatus, non-transitory computer readable medium, and image processing method | |
| CN109146873B (en) | Learning-based intelligent detection method and device for defects of display screen | |
| CN107578168B (en) | Method and device for defect library transplantation and electronic equipment | |
| CN106780464A (en) | A kind of fabric defect detection method based on improvement Threshold segmentation | |
| CN111243601A (en) | Voiceprint clustering method and device, electronic equipment and computer-readable storage medium | |
| CN109300127A (en) | Defect inspection method, device, computer equipment and storage medium | |
| CN109283182A (en) | A kind of detection method of battery welding point defect, apparatus and system | |
| CN111462056B (en) | Workpiece surface defect detection method, device, equipment and storage medium | |
| CN112275807A (en) | Method and device for detecting edge platform of hot-rolled strip steel profile | |
| US11386538B2 (en) | Image processing apparatus, image processing method, and storage medium | |
| CN109685756A (en) | Image feature automatic identifier, system and method | |
| CN113469293A (en) | Panel array short circuit detection method and device, electronic equipment and storage medium | |
| CN109102486B (en) | Surface defect detection method and device based on machine learning | |
| CN108416790B (en) | Method for detecting breakage rate of workpiece | |
| CN111967595B (en) | Candidate frame labeling method and system, model training method and target detection method | |
| CN113112126A (en) | Water supply pipe leakage early warning method and system based on artificial intelligence | |
| CN112750038A (en) | Transaction risk determination method and device and server | |
| CN110516589B (en) | Accurate boundary identification method for pipeline magnetic flux leakage data | |
| CN110017998B (en) | Vehicle detection method, device and equipment | |
| CN112434585A (en) | Method, system, electronic device and storage medium for identifying virtual reality of lane line | |
| CN105913440A (en) | Bimodal discrimination based fabric material surface defect segmenting method | |
| CN105469141A (en) | Neural-network-based prediction method and system | |
| JP2020135659A (en) | Parameter determination method, parameter determination device, and program |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |