CN114239323B - Root cause positioning method, device, equipment, medium and product for production abnormity - Google Patents
Root cause positioning method, device, equipment, medium and product for production abnormity Download PDFInfo
- Publication number
- CN114239323B CN114239323B CN202210162510.3A CN202210162510A CN114239323B CN 114239323 B CN114239323 B CN 114239323B CN 202210162510 A CN202210162510 A CN 202210162510A CN 114239323 B CN114239323 B CN 114239323B
- Authority
- CN
- China
- Prior art keywords
- virtual parallel
- history information
- target
- virtual
- information
- 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
- 238000000034 method Methods 0.000 title claims abstract description 73
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 49
- 230000002159 abnormal effect Effects 0.000 claims abstract description 46
- 206010013496 Disturbance in attention Diseases 0.000 claims abstract description 39
- 239000000047 product Substances 0.000 claims description 112
- 230000007547 defect Effects 0.000 claims description 22
- 230000015654 memory Effects 0.000 claims description 17
- 238000001914 filtration Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 12
- 230000005856 abnormality Effects 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 11
- 230000002950 deficient Effects 0.000 claims description 9
- 239000006227 byproduct Substances 0.000 claims description 7
- 238000009826 distribution Methods 0.000 claims description 7
- 238000003860 storage Methods 0.000 claims description 7
- 238000004891 communication Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 238000011031 large-scale manufacturing process Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000004807 localization Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000013515 script Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000009827 uniform distribution Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Factory Administration (AREA)
Abstract
The embodiment of the application provides a method, a device, equipment, a medium and a product for positioning root causes of abnormal production, wherein the method comprises the steps of obtaining equipment history information and reject ratio information of target batches of products; constructing a plurality of virtual parallel units along a target path based on the history information of the target level in the device history information; obtaining a bad concentration value of each virtual parallel unit based on equipment record information and bad rate information of the target batch of products; and determining an abnormal root factor based on the poor concentration value of each virtual parallel unit. The method can improve the accuracy of poor root cause positioning; particularly, for the condition that the data is less when sudden bad occurs in the production process of the product, the accuracy of the bad root positioning can be obviously improved, and the technical problem of low accuracy of the product production process root positioning is solved.
Description
Technical Field
The invention relates to the technical field of production control, in particular to a method, a device, equipment, a medium and a product for positioning root causes of production abnormity.
Background
The production process (for example, panel production) generally includes a plurality of production links, and each production process involves a large number of complex processes, which are performed by a series of devices configured in series or in parallel. In actual production, facing large-scale production equipment, it becomes more difficult to perform effective equipment management and control and to influence the positioning analysis of product quality. Especially when sudden abnormal faults occur, the root cause positioning accuracy is low.
Disclosure of Invention
The application mainly aims to provide a root cause positioning method, device, equipment, medium and product for abnormal production, and solve the technical problem of low root cause positioning accuracy in the production process of the existing product.
To achieve the above object, an embodiment of the present application provides a method for locating a root cause of a production anomaly, including:
acquiring equipment history information and reject ratio information of target batches of products; the equipment history information comprises history information of root cause units of the target batch products at different levels;
constructing a plurality of virtual parallel units along a target path based on the history information of the target level in the device history information; wherein the target path is a path of the target batch product at the target level; the virtual parallel units comprise virtual units generated by products in the target batch of products passing through root cause units in the target hierarchy;
obtaining a bad concentration value of each virtual parallel unit based on equipment record information and bad rate information of the target batch of products;
and determining an abnormal root factor based on the poor concentration value of each virtual parallel unit.
Optionally, before the step of constructing a plurality of virtual parallel units along the target path based on the history information of the target level in the device history information, the method further includes:
removing history information corresponding to root cause units with the sheet passing rate values lower than the sheet passing rate threshold value in the equipment history information to obtain filtering equipment history information;
the step of constructing a plurality of virtual parallel units along a target path based on the history information of the target level in the device history information includes:
and constructing a plurality of virtual parallel units along the target path based on the history information of the target level in the history information of the filtering equipment.
In this embodiment, the root cause unit having a low over-chipping rate has a low reliability because the sample size is small, and therefore, the corresponding history information is removed, and the accuracy of the abnormal root cause determination result can be improved and the calculation speed can be increased.
Optionally, the step of constructing a plurality of virtual parallel units along the target path based on the history information of the target level in the history information of the filtering device includes:
obtaining a target path based on the history information of the target level in the history information of the filtering equipment;
and constructing a plurality of virtual parallel units along the target path based on the history information of the target level in the history information of the filtering equipment.
In this embodiment, the target path is obtained by using the history information of the target hierarchy in advance, and the efficiency of constructing the virtual parallel unit can be increased.
Optionally, the step of obtaining the defect concentration value of each virtual parallel unit based on the equipment history information and the defect rate information of the target batch of products includes:
the product in-out time of each virtual unit in the virtual parallel units is subjected to simplification processing so as to update the equipment history information and the reject ratio information;
and obtaining a defect concentration value of each virtual parallel unit based on the updated equipment history information and the updated defect rate information.
In this embodiment, the product entry and exit times of the virtual units in the virtual parallel units are unified, so that the time of the product passing through a certain unit is unified, and the influence caused by repeated processing information can be avoided. It can be understood that repeated processing may generate multiple bad information for a bad product, which may cause inaccuracy of the bad rate information and affect the judgment of the root cause.
Optionally, the step of performing a singulation process on the product entry and exit times of each virtual unit in the virtual parallel units to update the equipment history information and the reject ratio information includes:
and taking the maximum value or the minimum value of the product entry and exit time of each virtual unit in the virtual parallel units to update the equipment history information and the reject ratio information.
In this embodiment, the maximum or minimum is easier to identify, and therefore, the processing efficiency is higher in the singulation process and more efficient for the entire algorithm process.
Optionally, the step of obtaining a defect concentration value of each of the virtual parallel units based on the updated device history information and the updated defect rate information includes:
obtaining a poor concentration value of each virtual parallel unit according to the following relation:
wherein ctro represents the poor concentration of the virtual parallel cells, TlabelRepresenting the real distribution of the defective rate of the virtual parallel units, UlabelIndicating the uniformity distribution of the defective rate of the virtual parallel cells, k indicating the non-uniformity of the virtual parallel cellsThe number of good products, m, represents the total amount of products involved for all virtual parallel units.
Optionally, the step of determining an abnormal root cause based on the poor concentration value of each of the virtual parallel units includes:
obtaining a bad interpretation value of a root cause unit corresponding to each virtual parallel unit based on the bad concentration value of each virtual parallel unit;
and determining abnormal root factors based on the bad interpretation value of the root factor unit corresponding to each virtual parallel unit.
In this embodiment, since the bad interpretation value directly corresponds to the root cause unit (i.e., site, equipment, etc.) of the entity, the bad interpretation value is obtained by using the bad concentration value, and the abnormal root cause is determined using the bad interpretation value as an index, so that the root cause unit with abnormal production can be more accurately located.
Optionally, the step of obtaining a bad interpretation value of a root cause unit corresponding to each virtual parallel unit based on the bad concentration value of each virtual parallel unit includes:
the bad interpretation value is obtained according to the following relation:
wherein, degree represents a poor interpretation degree, ctro represents a poor concentration degree, Is represents a product failure rate of the virtual parallel unit, and pv represents a film passing rate of the virtual parallel unit.
Optionally, the step of determining an abnormal root cause based on the bad interpretation value of the root cause unit corresponding to each virtual parallel unit includes:
and determining an abnormal root factor according to the abnormal condition of the bad interpretation value of each virtual parallel unit.
In this embodiment, it is easier to determine an abnormality of a set of values, and therefore, an abnormality of a poor interpretation value can be determined more quickly and efficiently as an abnormality root cause
Optionally, the root cause unit includes: at least one of a station, a device, a sub-device, and a chamber.
In addition, in order to achieve the above object, an embodiment of the present application further provides a root cause locating device for a production abnormality, including:
the data acquisition module is used for acquiring equipment record information and reject ratio information of target batch products; the equipment history information comprises history information of root cause units of the target batch products at different levels;
the virtual construction module is used for constructing a plurality of virtual parallel units along a target path based on the history information of the target level in the equipment history information; wherein the target path is a path of the target batch product at the target level; the virtual parallel units comprise virtual units generated by products in the target batch of products passing through root cause units in the target hierarchy;
the variable obtaining module is used for obtaining a bad concentration value of each virtual parallel unit based on equipment record information and bad rate information of the target batch of products;
and the root cause determining module is used for determining abnormal root causes based on the poor concentration values of the virtual parallel units.
In addition, to achieve the above object, the present application further provides an electronic device, which includes a memory and a processor, where the memory stores a computer program, and the processor executes the computer program to implement the foregoing method.
In addition, to achieve the above object, the present application further provides a computer readable storage medium, where a computer program is stored, and a processor executes the computer program to implement the foregoing method.
Furthermore, to achieve the above object, the present application also provides a computer program product, which when being processed, realizes the aforementioned method.
Compared with the prior art, the invention has the beneficial effects that:
the embodiment of the application provides a method, a device, equipment, a medium and a product for positioning root causes of abnormal production, wherein the method comprises the steps of obtaining equipment history information and reject ratio information of target batches of products; the equipment history information comprises history information of root cause units of the target batch products at different levels; constructing a plurality of virtual parallel units along a target path based on the history information of the target level in the device history information; wherein the target path is a path of the target batch product at the target level; the virtual parallel units comprise virtual units generated by each product of the target batch of products passing through a root cause unit in the target level; obtaining a bad concentration value of each virtual parallel unit based on equipment record information and bad rate information of the target batch of products; and determining an abnormal root factor based on the poor concentration value of each virtual parallel unit. Namely, the method establishes more analyzable parallel units by constructing the virtual parallel units, and defines a poor concentration index which can represent the abnormal root cause unit of each hierarchy based on the analyzable parallel units. Because more basic data are constructed, the accuracy of poor root cause positioning can be improved; particularly, for the condition that the data is less when sudden bad occurs in the production process of the product, the accuracy of the bad root positioning can be obviously improved, and the technical problem of low accuracy of the product production process root positioning is solved.
Drawings
Fig. 1 is a schematic structural diagram of an electronic device in a hardware operating environment according to an embodiment of the present application;
FIG. 2 is a flowchart illustrating a method for locating a root cause of a production anomaly according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a target level building virtual parallel unit in an embodiment of the present application;
FIG. 4 is a flowchart illustrating an embodiment of step S60 in FIG. 2;
FIG. 5 is a flowchart illustrating an embodiment of step S80 in FIG. 2;
fig. 6 is a functional block diagram of a cause locating device for a production anomaly according to an embodiment of the present application.
The implementation, functional features and advantages of the objectives of the present application will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The main solution of the embodiment of the application is as follows: the method comprises the steps of obtaining equipment history information and reject ratio information of target batch products; the equipment history information comprises history information of root cause units of the target batch products at different levels; constructing a plurality of virtual parallel units along a target path based on the history information of the target level in the device history information; wherein the target path is a path of the target batch product at the target level; the virtual parallel units comprise virtual units generated by products in the target batch of products passing through root cause units in the target hierarchy; obtaining a bad concentration value of each virtual parallel unit based on equipment record information and bad rate information of the target batch of products; and determining an abnormal root factor based on the poor concentration value of each virtual parallel unit.
The manufacturing and production process of the current panel is very complicated, the panel usually comprises the technologies of Array, CF, Cell, modules and the like, the control unit can be stacked on the substrate layer by layer, the color is controlled through the RGB unit, then the glass is cut into the specifications of the sizes of products such as mobile phones and television screens, and finally other relevant units are embedded through the module sections. Each process flow involves a large number of complex processes that are performed by a series of devices configured in series or in parallel. In actual production, facing large-scale production equipment, it becomes more difficult to perform effective equipment management and control and to influence the positioning analysis of product quality. Especially when a sudden abnormal fault occurs, the amount of analyzable samples is very small, which brings more challenges to root cause localization analysis.
The application provides a solution, and more analyzable parallel units are established by constructing virtual parallel units, and based on the virtual parallel units, a poor concentration index capable of expressing the abnormity of each level root cause unit is defined. Because more basic data are constructed, the accuracy of poor root cause positioning can be improved; particularly, for the condition that the data is less when sudden bad occurs in the production process of the product, the accuracy of the bad root positioning can be obviously improved, and the technical problem of low accuracy of the product production process root positioning is solved.
Referring to fig. 1, fig. 1 is a schematic structural diagram of an electronic device in a hardware operating environment according to an embodiment of the present application.
As shown in fig. 1, the electronic device may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a WIreless interface (e.g., a WIreless-FIdelity (WI-FI) interface). The Memory 1005 may be a Random Access Memory (RAM) Memory, or may be a Non-Volatile Memory (NVM), such as a disk Memory. The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the configuration shown in fig. 1 does not constitute a limitation of the electronic device and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is a storage medium, may include therein an operating system, a data storage module, a network communication module, a user interface module, and an electronic program.
In the electronic apparatus shown in fig. 1, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the electronic device according to the present invention may be disposed in the electronic device, and the electronic device calls the root cause positioning apparatus of the production anomaly stored in the memory 1005 through the processor 1001 and executes the root cause positioning method of the production anomaly provided in the embodiment of the present application.
Referring to fig. 2, an embodiment of the present application provides a root cause localization method for a production anomaly, including:
s20, acquiring equipment history information and reject ratio information of the target batch of products; the equipment history information comprises history information of root cause units of the target batch products at different levels.
In the specific implementation process, the product refers to an industrial product, and in this embodiment, the product may include a panel. The target batch of product refers to any batch of product, and the production of the same batch of product is generally continuous. Therefore, the present embodiment targets the batch of products.
The device resume information includes circulation information in the production process of the product, that is, which links on the production line are accessed at specific time points. In this embodiment, the links on the production line can be layered, for example, the shelves are from large to small, such as stations, equipment, sub-equipment, cavities, and the like. Therefore, the device history information includes history information of root cause units of the target batch of products at different levels.
The reject ratio information refers to the ratio of defective products in the target batch of products, and the reject ratio information is acquired for calculating the subsequent defective concentration ratio.
Note that the root cause unit refers to a link in which a failure occurs, that is, a site, equipment, a sub-equipment, a cavity, and the like. The method of the embodiment is to more accurately locate the root cause unit of the production abnormality through a small amount of data.
S40, constructing a plurality of virtual parallel units along the target path based on the history information of the target level in the equipment history information; wherein the target path is a path of the target batch product at the target level; the virtual parallel units comprise virtual units generated by products in the target batch of products passing through the root cause unit in the target level.
In the specific implementation process, the target hierarchy refers to any one of different hierarchies, and it is understood that, when each hierarchy is executed according to the method of the present embodiment, a virtual parallel unit of each hierarchy can be constructed. The resume information of the target level comprises the circulation information of the target batch product at the level.
Specifically, taking the target level (site level) as an example, the target path is a path of the target batch of products on each site. Referring to fig. 3, fig. 3 is a schematic diagram of the target level building of virtual parallel units. In the figure, u represents a site, a row represents a root cause unit (i.e., a site) passed by a single product in a target batch of products in a site level, m represents the number of products in the target batch of products, and k represents the number of sites taken in the site level. Then combining the virtual root cause units generated by the same station through which each product in the target batch of products passes into a virtual parallel unit, namelyvtm 1 、vtm 2 、vtm 3 ..。
The virtual parallel unit thus formed includes a plurality of virtual root cause units (also referred to as virtual units in this embodiment), so that a larger number of samples are constructed (i.e., a larger number of analyzable parallel units are created), and based on the larger number of samples in the virtual parallel unit, the abnormal root cause points are easier to be analyzed accurately.
And S60, obtaining the defect concentration value of each virtual parallel unit based on the equipment history information and the defect rate information of the target batch of products.
In particular implementations, the poor concentration value may characterize the degree of poor concentration of the virtual parallel units. The poor concentration degree can reflect the poor distribution condition of the virtual units in the virtual parallel units, and further can be used as the basis for subsequently determining the abnormal root cause unit.
In an alternative embodiment, referring to fig. 4, the step of obtaining the defect concentration value of each virtual parallel unit based on the equipment history information and the defect rate information of the target batch of products includes:
s601, conducting simplification processing on product in-out time of each virtual unit in the virtual parallel units so as to update the equipment history information and the reject ratio information;
in the specific implementation process, the product entry and exit time refers to the time when the product arrives at a certain unit and the time when the product leaves the unit, and belongs to the history information. The product in and out time may indicate whether the product is processed through a unit or not. The product in-out time of each virtual unit in the virtual parallel units is subjected to simplification processing, so that the time of the product passing through a certain unit is unified, and the influence caused by repeated processing information can be avoided. It can be understood that repeated processing may generate multiple bad information for a bad product, which may cause inaccuracy of the bad rate information and affect the judgment of the root cause.
It is understood that the manner of singulation process may include a variety of ways as long as one is taken at all in and out times. As an alternative embodiment, the specific way of the singulation process may be to take the maximum or minimum value of the product in-out time (Qtime) on each virtual cell. In this embodiment, the maximum or minimum is easier to identify, and therefore, the processing efficiency is higher in the singulation process and more efficient for the entire algorithm process.
And S602, obtaining a defect concentration value of each virtual parallel unit based on the updated equipment history information and the updated defect rate information.
In the specific implementation process, the updated equipment history information and the updated reject ratio information are obtained by simplifying the product entry and exit time of each virtual unit in the virtual parallel units. Therefore, the poor concentration value of each virtual parallel unit obtained based on the poor concentration value is more accurate.
Specifically, the step of obtaining the defect concentration value of each virtual parallel unit based on the updated device history information and the updated defect rate information includes:
obtaining a poor concentration value of each virtual parallel unit according to the following relation:
wherein ctro represents the poor concentration of the virtual parallel cells, TlabelRepresenting the real distribution of the defective rate of the virtual parallel units, UlabelThe defect rate uniformity distribution of the virtual parallel units is represented, k represents the number of defective products of the virtual parallel units, and m represents the total number of products related to all the virtual parallel units.
It will be appreciated that, as in the above expressions,
And S80, determining an abnormal root factor based on the poor concentration value of each virtual parallel unit.
In a specific implementation process, the poor concentration degree of the virtual parallel units can be represented by the poor concentration degree value, so that the obviously abnormal root cause unit can be judged according to the poor concentration degree value conditions of different virtual parallel units.
As an alternative embodiment, referring to fig. 5, the step of determining an abnormal root cause based on the poor concentration value of each of the virtual parallel units includes:
s801, obtaining a bad interpretation value of a root cause unit corresponding to each virtual parallel unit based on the bad concentration value of each virtual parallel unit;
in a specific implementation, each virtual parallel unit corresponds to a root cause unit (e.g., a site) in the target hierarchy. The poor concentration value can represent the degree of poor concentration of the virtual parallel cells, but the target object is the virtual parallel cells, and in order to more accurately identify abnormal root elements, it is necessary to determine indexes of the root elements. Therefore, the bad interpretation value of the root cause unit corresponding to each virtual parallel unit is obtained.
Specifically, the step of obtaining a bad interpretation value of a root cause unit corresponding to each virtual parallel unit based on the bad concentration value of each virtual parallel unit includes:
the bad interpretation value is obtained according to the following relation:
wherein, degree represents a poor interpretation degree, ctro represents a poor concentration degree, Is represents a product failure rate of the virtual parallel unit, and pv represents a film passing rate of the virtual parallel unit.
Wherein,
the number of products processed by the ith root cause unit is referred to as cnt, and the cnt is the total number of products in the target batch.
S802, determining abnormal root factors based on the bad interpretation values of the root factor units corresponding to the virtual parallel units.
In the specific implementation process, there are various ways to determine the abnormal root cause according to the poor interpretation value, such as observation of obvious abnormal value, threshold comparison, etc. Specifically, the bad interpretation values of all root cause units may be sorted, and then the root cause unit corresponding to a higher value may be taken as the abnormal root cause.
In this embodiment, since the bad interpretation value directly corresponds to the root cause unit (i.e., site, equipment, etc.) of the entity, the bad interpretation value is obtained by using the bad concentration value, and the abnormal root cause is determined using the bad interpretation value as an index, so that the root cause unit with abnormal production can be more accurately located.
As an optional implementation manner, the step of determining an abnormal root cause based on the bad interpretation value of the root cause unit corresponding to each virtual parallel unit includes: and determining abnormal root causes according to the abnormal conditions of the bad interpretation values of the root cause units corresponding to the virtual parallel units.
In the specific implementation process, the abnormity of a group of values is easier to judge, so that the abnormity of the poor interpretation value can be judged quickly and efficiently.
It should be understood that the above is only an example, and the technical solution of the present application is not limited in any way, and those skilled in the art can make the setting based on the actual application, and the setting is not limited herein.
As can be easily found from the above description, the method of this embodiment establishes more analyzable parallel units by constructing virtual parallel units, and defines a poor concentration index that can represent the anomaly of the root cause unit of each hierarchy based on the more analyzable parallel units. Because more basic data are constructed, the accuracy of poor root cause positioning can be improved; particularly, for the condition that the data is less when sudden bad occurs in the production process of the product, the accuracy of the bad root positioning can be obviously improved, and the technical problem of low accuracy of the product production process root positioning is solved.
In the prior art, in the face of a production line of large-scale production equipment, if a bad root cause needs to be accurately positioned, a large amount of data of a complete generation process of each equipment needs to be obtained. However, in the actual production process, sudden abnormal faults often occur, and at the moment, the number of analysis samples is small, and data of the complete production process is not available. The method of the embodiment can accurately locate the abnormal root cause under the condition of a small number of samples.
In one embodiment, before the step of constructing a plurality of virtual parallel units along the target path based on the target level history information in the device history information, the method further comprises:
removing history information corresponding to root cause units with the sheet passing rate values lower than the sheet passing rate threshold value in the equipment history information to obtain filtering equipment history information;
in a specific implementation process, the threshold of the sheet passing rate may be set and obtained through experience or historical test data, which is not described herein again.
It can be understood that the root cause unit with the low film passing rate has low reliability due to the small sample size, so that the corresponding history information is removed, and the accuracy of the abnormal root cause determination result can be improved, and the calculation speed can be increased.
Correspondingly, the step of constructing a plurality of virtual parallel units along the target path based on the history information of the target level in the device history information includes:
and constructing a plurality of virtual parallel units along the target path based on the history information of the target level in the history information of the filtering equipment.
In the specific implementation process, the subsequent calculation is carried out by using the history information of the filtering equipment, so that the accuracy of the determination result of the abnormal root cause can be improved, and the calculation speed can be increased.
Specifically, the step of constructing a plurality of virtual parallel units along the target path based on the history information of the target level in the history information of the filtering device includes:
obtaining a target path based on the history information of the target level in the history information of the filtering equipment;
and constructing a plurality of virtual parallel units along the target path based on the history information of the target level in the history information of the filtering equipment.
In the specific implementation process, the target path is obtained by utilizing the history information of the target level in advance, so that the construction efficiency of the virtual parallel unit can be improved.
In addition, it can be understood that the method of the above embodiment processes the root cause unit of the target hierarchy, and in the actual application process, the determination of all abnormal root causes can be realized as long as the method of the present embodiment is repeatedly executed for each hierarchy.
Referring to fig. 6, based on the same inventive principle, an embodiment of the present application further provides a root cause locating device for a production abnormality, including:
the data acquisition module is used for acquiring equipment record information and reject ratio information of target batch products; the equipment history information comprises history information of root cause units of the target batch products at different levels;
the virtual construction module is used for constructing a plurality of virtual parallel units along a target path based on the history information of the target level in the equipment history information; wherein the target path is a path of the target batch product at the target level; the virtual parallel units comprise virtual units generated by products in the target batch of products passing through root cause units in the target hierarchy;
the variable obtaining module is used for obtaining a bad concentration value of each virtual parallel unit based on equipment record information and bad rate information of the target batch of products;
and the root cause determining module is used for determining abnormal root causes based on the poor concentration values of the virtual parallel units.
It should be noted that, in this embodiment, each module in the root cause positioning device for the production abnormality corresponds to each step in the root cause positioning method for the production abnormality in the foregoing embodiment one by one, and therefore, the specific implementation of this embodiment may refer to the implementation of the root cause positioning method for the production abnormality, and is not described here again.
Furthermore, to achieve the above object, the present application also provides an electronic device, which includes a processor, a memory and a computer program stored in the memory, wherein the computer program, when executed by the processor, implements the steps of the method in the foregoing embodiments.
Furthermore, in an embodiment, the present application further provides a computer storage medium having a computer program stored thereon, where the computer program is executed by a processor to implement the steps of the method in the foregoing embodiments.
In some embodiments, the computer-readable storage medium may be memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash, magnetic surface memory, optical disk, or CD-ROM; or may be various devices including one or any combination of the above memories. The computer may be a variety of computing devices including intelligent terminals and servers.
In some embodiments, executable instructions may be written in any form of programming language (including compiled or interpreted languages), in the form of programs, software modules, scripts or code, and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.
By way of example, executable instructions may correspond, but do not necessarily have to correspond, to files in a file system, and may be stored in a portion of a file that holds other programs or data, such as in one or more scripts in a hypertext Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub-programs, or portions of code).
By way of example, executable instructions may be deployed to be executed on one computing device or on multiple computing devices at one site or distributed across multiple sites and interconnected by a communication network.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (e.g., a rom/ram, a magnetic disk, an optical disk) and includes instructions for enabling a multimedia terminal (e.g., a mobile phone, a computer, a television receiver, or a network device) to execute the method according to the embodiments of the present application.
The above description is only a preferred embodiment of the present application, and not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings of the present application, or which are directly or indirectly applied to other related technical fields, are included in the scope of the present application.
Claims (12)
1. A method for locating a root cause of a production abnormality, comprising:
acquiring equipment history information and reject ratio information of target batches of products; the equipment record information comprises record information of root cause units of the target batch of products at different levels, the record information comprises circulation information in the production process of the products, and the root cause units are links with failures;
constructing a plurality of virtual parallel units along a target path based on the history information of the target level in the device history information; wherein the target path is a path of the target batch product at the target level; the virtual parallel units comprise virtual units generated by products in the target batch of products passing through the same root cause unit in the target level, and the target level is any one of different levels;
obtaining a bad concentration value of each virtual parallel unit based on equipment record information and bad rate information of the target batch of products; wherein the poor concentration value is a value representing a degree of poor concentration of the virtual parallel units;
and determining an abnormal root factor based on the poor concentration value of each virtual parallel unit.
2. The method of claim 1, wherein the step of constructing a plurality of virtual parallel units along the target path based on the target level history information in the device history information further comprises:
removing history information corresponding to root cause units with the sheet passing rate values lower than the sheet passing rate threshold value in the equipment history information to obtain filtering equipment history information;
the step of constructing a plurality of virtual parallel units along a target path based on the history information of the target level in the device history information includes:
and constructing a plurality of virtual parallel units along the target path based on the history information of the target level in the history information of the filtering equipment.
3. The method of claim 2, wherein the step of constructing a plurality of virtual parallel units along the target path based on the history information of the target level in the history information of the filtering apparatus comprises:
obtaining a target path based on the history information of the target level in the history information of the filtering equipment;
and constructing a plurality of virtual parallel units along the target path based on the history information of the target level in the history information of the filtering equipment.
4. The method of claim 1, wherein the step of obtaining the defect concentration value of each virtual parallel unit based on the equipment history information and the defect rate information of the target batch of products comprises:
the product in-out time of each virtual unit in the virtual parallel units is subjected to simplification processing so as to update the equipment history information and the reject ratio information;
and obtaining a defect concentration value of each virtual parallel unit based on the updated equipment history information and the updated defect rate information.
5. The method as claimed in claim 4, wherein the step of singulating the product entry and exit times of the virtual parallel units to update the equipment history information and the fraction defective information comprises:
and taking the maximum value or the minimum value of the product entry and exit time of each virtual unit in the virtual parallel units to update the equipment history information and the reject ratio information.
6. The method of claim 4, wherein the step of obtaining a defect concentration value for each of the virtual parallel units based on the updated equipment history information and the updated defect rate information comprises:
obtaining a poor concentration value of each virtual parallel unit according to the following relation:
wherein,
indicating a poor concentration of virtual parallel cells,
representing virtualThe fraction defective of the parallel units is distributed truly,
the defect rate uniformity distribution of the virtual parallel units is represented, k represents the number of defective products of the virtual parallel units, and m represents the total number of products related to all the virtual parallel units.
7. The method of claim 1, wherein the step of determining an anomaly root cause based on the poor concentration value of each of the virtual parallel units comprises:
obtaining a bad interpretation value of a root cause unit corresponding to each virtual parallel unit based on the bad concentration value of each virtual parallel unit;
determining abnormal root factors based on the bad interpretation values of the root factor units corresponding to the virtual parallel units;
the step of obtaining a bad interpretation value of a root cause unit corresponding to each virtual parallel unit based on the bad concentration value of each virtual parallel unit includes:
the bad interpretation value is obtained according to the following relation:
wherein, degree represents a poor interpretation degree, ctro represents a poor concentration degree, Is represents a product failure rate of the virtual parallel unit, and pv represents a film passing rate of the virtual parallel unit.
8. The method of claim 6, wherein the step of determining abnormal root causes based on the bad interpretation value of the root cause unit corresponding to each of the virtual parallel units comprises:
and determining an abnormal root factor according to the abnormal condition of the bad interpretation value of each virtual parallel unit.
9. The method of any one of claims 1-8, wherein the root cause unit comprises: at least one of a station, a device, a sub-device, and a chamber.
10. A root cause locating device for production abnormality is characterized by comprising:
the data acquisition module is used for acquiring equipment record information and reject ratio information of target batch products; the equipment record information comprises record information of root cause units of the target batch of products at different levels, the record information comprises circulation information in the production process of the products, and the root cause units are links with failures;
the virtual construction module is used for constructing a plurality of virtual parallel units along a target path based on the history information of the target level in the equipment history information; wherein the target path is a path of the target batch product at the target level; the virtual parallel units comprise virtual units generated by products in the target batch of products passing through the same root cause unit in the target level, and the target level is any one of different levels;
the variable obtaining module is used for obtaining a bad concentration value of each virtual parallel unit based on equipment record information and bad rate information of the target batch of products; wherein the poor concentration value is a value representing a degree of poor concentration of the virtual parallel units;
and the root cause determining module is used for determining abnormal root causes based on the poor concentration values of the virtual parallel units.
11. An electronic device, characterized in that the electronic device comprises a memory in which a computer program is stored and a processor, which executes the computer program, implementing the method according to any of claims 1-9.
12. A computer-readable storage medium, having a computer program stored thereon, which, when executed by a processor, performs the method of any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210162510.3A CN114239323B (en) | 2022-02-22 | 2022-02-22 | Root cause positioning method, device, equipment, medium and product for production abnormity |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210162510.3A CN114239323B (en) | 2022-02-22 | 2022-02-22 | Root cause positioning method, device, equipment, medium and product for production abnormity |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114239323A CN114239323A (en) | 2022-03-25 |
| CN114239323B true CN114239323B (en) | 2022-04-26 |
Family
ID=80747744
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210162510.3A Active CN114239323B (en) | 2022-02-22 | 2022-02-22 | Root cause positioning method, device, equipment, medium and product for production abnormity |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114239323B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117389230B (en) * | 2023-11-16 | 2024-06-07 | 广州中健中医药科技有限公司 | Antihypertensive traditional Chinese medicine extract production control method and system |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111159645B (en) * | 2019-12-19 | 2023-06-06 | 成都数之联科技股份有限公司 | Bad root cause positioning method based on product production histories and parameters |
| CN112269818B (en) * | 2020-11-25 | 2023-11-21 | 成都数之联科技股份有限公司 | Equipment parameter root cause positioning method, system, device and medium |
| CN113450065B (en) * | 2021-05-27 | 2024-01-26 | 中国电建集团西北勘测设计研究院有限公司 | Production operation management system and method for wind power plant |
| CN114036826A (en) * | 2021-10-29 | 2022-02-11 | 深圳前海微众银行股份有限公司 | Model training method, root cause determination method, device, equipment and storage medium |
-
2022
- 2022-02-22 CN CN202210162510.3A patent/CN114239323B/en active Active
Non-Patent Citations (1)
| Title |
|---|
| 李泉.根因分析法在预防精神科口服给药错误管理中的应用.《心理月刊》.2019,(第03期), * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114239323A (en) | 2022-03-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113935497A (en) | Intelligent operation and maintenance fault processing method, device and equipment and storage medium thereof | |
| CN114239323B (en) | Root cause positioning method, device, equipment, medium and product for production abnormity | |
| CN116882321B (en) | Meteorological influence quantitative evaluation method and device, storage medium and electronic equipment | |
| CN114357812B (en) | Product reliability test method and device, computer equipment and storage medium | |
| CN113379098A (en) | River interval dynamic flood peak analysis early warning method, system, equipment and medium | |
| CN111881023A (en) | Software aging prediction method and device based on multi-model comparison | |
| CN115392037A (en) | Equipment fault prediction method, device, equipment and storage medium | |
| CN116091874B (en) | Image verification method, training method, device, medium, equipment and program product | |
| CN114611799B (en) | Time sequence neural network new energy output multi-step prediction method based on supervised learning | |
| CN113988325A (en) | Power system fault early warning method and device, terminal equipment and storage medium | |
| CN115277261A (en) | Abnormal machine intelligent identification method, device and equipment based on industrial control network virus | |
| CN115841046A (en) | Accelerated degradation test data processing method and device based on wiener process | |
| CN115616412A (en) | Energy storage battery pack modeling method, device, equipment and readable storage medium | |
| CN111767193A (en) | Server data anomaly detection method and device, storage medium and equipment | |
| CN111340287A (en) | Power distribution cabinet operation state prediction method and device | |
| CN112950908B (en) | Data monitoring and early warning method, system, medium and electronic terminal | |
| CN113793049B (en) | Method, device, equipment and medium for positioning bad root cause in production process of product | |
| CN113570070B (en) | Streaming data sampling and model updating method, device, system and storage medium | |
| CN115238596B (en) | Data processing method and device, readable storage medium and electronic equipment | |
| CN116679139A (en) | Cable replacement monitoring system and method | |
| CN115563775A (en) | Power simulation method and device, electronic device and storage medium | |
| CN112231194B (en) | Index abnormity root analysis method and device and computer readable storage medium | |
| CN115358348A (en) | Vehicle straight-through rate influence characteristic determination method, device, equipment and medium | |
| CN114416596A (en) | Application testing method and device, computer equipment and storage medium | |
| CN112397404B (en) | Semiconductor process detection method and system |
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 | ||
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20220325 Assignee: Chengdu Haijixian Intelligent Technology Co.,Ltd. Assignor: Chengdu shuzhilian Technology Co.,Ltd. Contract record no.: X2024510000011 Denomination of invention: Root cause localization methods, devices, equipment, media, and products for production abnormalities Granted publication date: 20220426 License type: Common License Record date: 20240717 |