KR102600584B1 - Vision system for building process data - Google Patents

Abstract

The purpose of the present invention is to provide a vision system for building process data that can perform the function of a production management system by complementing existing process lines at a lower cost.
In order to achieve the above purpose, the vision system for constructing process data according to the first embodiment of the present invention is a 7-segment system that displays data formed in the form of 7-segments regarding production management status or process management status. -Segment display; an input unit that receives data displayed on the 7-segment display unit; A server having a DB that receives data from the input unit in real time and stores and manages the data; and a monitoring unit that monitors or analyzes data stored in the server.

Description

Vision system for building process data {VISION SYSTEM FOR BUILDING PROCESS DATA}

The present invention relates to a vision system for building process data, and more specifically, to a vision system for building process data that can perform the function of a production management system (Manufacturing Execution System) by complementing existing process lines at a low cost. It's about.

Recently, as the era of the Fourth Industrial Revolution opens, various smart devices are starting to take root around us.

At the same time, factory production methods are also changing.

A smart factory is a factory that produces products at minimum cost and time by introducing ICT (information and communication technology) throughout the entire process, including planning, design, production, distribution, and sales.

Unlike existing factories where only simple tasks are automated, smart factories introduce systems such as production management system, enterprise resource planning, product lifecycle management, and supply chain management. It replaces the role of humans and shows performance that processes things more accurately than humans.

In this way, if various production data generated in the field can be aggregated, analyzed, and viewed in real time, efficient production management is possible.

This smart factory system is called a production management system or process management system.

The production management system is the most widely used system in smart factories built to date.

In other words, it is a system that replaces the labor force in the production process.

This is not only more accurate than field workers, but also reduces the work required by workers because there is no need to directly record the process status, making it more efficient.

However, equipment installation of the production management system requires large expenditures.

It is not easy for small and medium-sized companies to bear this burden.

Even if you spend a large amount of money to install production management system system equipment or replace existing equipment with production management system equipment, there may not be a significant change in the company's sales. In this case, it is reasonable to install production management system system equipment. There was a problem that wasn't there.

Republic of Korea Patent Publication No. 10-2064490 (announced on January 10, 2020)

The purpose of the present invention to solve the conventional problems described above is to provide a vision system for building process data that can perform the function of a production management system by complementing existing process lines at a lower cost.

In order to achieve the above purpose, the vision system for constructing process data according to the first embodiment of the present invention is a 7-segment system that displays data formed in the form of 7-segments regarding production management status or process management status. -Segment display; an input unit that receives data displayed on the 7-segment display unit; A server having a DB that receives data from the input unit in real time and stores and manages the data; and a monitoring unit that monitors or analyzes data stored in the server.

In order to achieve the above purpose, the vision system for constructing process data according to the second embodiment of the present invention is a 7-segment system that displays data formed in the form of 7-segments regarding production management status or process management status. -Segment display; an input unit that receives data displayed on the 7-segment display unit; A server having a DB that receives data from the input unit in real time and stores and manages the data; and a monitoring unit that monitors or analyzes data stored in the server, wherein the input unit includes: a photographing unit that photographs data formed in the 7-segment form; and a learning module that performs learning to read data captured by the photographing unit.

In order to achieve the above purpose, the vision system for building process data according to the third embodiment of the present invention is a 7-segment system that displays data formed in the form of 7-segments regarding production management status or process management status. -Segment display; an input unit that receives data displayed on the 7-segment display unit; A server having a DB that receives data from the input unit in real time and stores and manages the data; and a monitoring unit that monitors or analyzes data stored in the server, wherein the server provides an alarm to the monitoring unit when data received from the input unit falls outside a predetermined normal range.

In order to achieve the above purpose, the vision system for constructing process data according to the fourth embodiment of the present invention is a 7-segment system that displays data formed in the form of 7-segments regarding production management status or process management status. -Segment display; an input unit that receives data displayed on the 7-segment display unit; A server having a DB that receives data from the input unit in real time and stores and manages the data; and a monitoring unit that monitors or analyzes data stored in the server, wherein the input unit includes: a photographing unit that photographs data formed in the 7-segment form; and a learning module that performs learning to read data captured by the photographing unit, and generates learning data for learning using the 7-segment display unit and the photographing unit, and the learning module Characterized in that learning is performed using the learning data.

In order to achieve the above purpose, the vision system for constructing process data according to the fifth embodiment of the present invention is a 7-segment system that displays data formed in the form of 7-segments regarding production management status or process management status. -Segment display; an input unit that receives data displayed on the 7-segment display unit; A server having a DB that receives data from the input unit in real time and stores and manages the data; and a monitoring unit that monitors or analyzes data stored in the server, wherein the monitoring unit is capable of searching data stored in the DB and visualizing the searched data.

Specific details of other embodiments are included in “Specific Details for Carrying Out the Invention” and the attached “Drawings.”

The advantages and/or features of the present invention and methods for achieving them will become clear by referring to the various embodiments described in detail below along with the accompanying drawings.

However, the present invention is not limited to the configuration of each embodiment disclosed below, but may also be implemented in various different forms. However, each embodiment disclosed in this specification ensures that the disclosure of the present invention is complete, and the present invention It is provided to fully inform those skilled in the art of the present invention, and it should be noted that the present invention is only defined by the scope of each claim.

According to the present invention, there is an effect of performing the function of a production management system by complementing the existing process line at a lower cost.

1 is a block diagram showing the overall configuration of a vision system for building process data according to the present invention.
Figure 2 is a diagram showing an embedded module of a vision system for building process data according to the present invention.
Figure 3 is a diagram showing the state in which primary learning is performed in the learning module of the vision system for building process data according to the present invention.
Figure 4 is a diagram showing the state in which secondary learning is performed in the learning module of the vision system for building process data according to the present invention.
Figure 5 is a diagram showing the state in which 3rd learning is performed in the learning module of the vision system for building process data according to the present invention.
Figure 6 is a diagram showing the state in which fourth learning has occurred in the learning module of the vision system for building process data according to the present invention.
Figure 7 is a diagram showing the state in which 5th learning has occurred in the learning module of the vision system for building process data according to the present invention.
Figure 8 is a diagram showing a state in which learning has been completed in the learning module of the vision system for building process data according to the present invention.
Figure 9 is a diagram showing data detected by the server of a vision system for building process data according to the present invention.
Figure 10 is a diagram showing a data set for each device displayed on the monitoring unit of the vision system for building process data according to the present invention.
Figure 11 is a diagram showing data for a specified period viewed from the monitoring unit of the vision system for building process data according to the present invention.
Figure 12 is a diagram showing login in the monitoring unit of the vision system for building process data according to the present invention.
Figure 13 is a diagram showing an alarm displayed when a data error occurs in the monitoring unit of the vision system for building process data according to the present invention.

Before explaining the present invention in detail, the terms or words used in this specification should not be construed as unconditionally limited to their ordinary or dictionary meanings, and the inventor of the present invention should not use the terms or words in order to explain his invention in the best way. It should be noted that the concepts of various terms can be appropriately defined and used, and furthermore, that these terms and words should be interpreted with meanings and concepts consistent with the technical idea of the present invention.

That is, the terms used in this specification are only used to describe preferred embodiments of the present invention, and are not used with the intention of specifically limiting the content of the present invention, and these terms refer to various possibilities of the present invention. It is important to note that this is a term defined with consideration in mind.

In addition, it should be noted that in this specification, singular expressions may include plural expressions, unless the context clearly indicates a different meaning, and may include singular meanings even if similarly expressed in plural. .

Throughout this specification, when a component is described as “including” another component, it does not exclude any other component, but includes any other component, unless specifically stated to the contrary. It could mean that you can do it.

Furthermore, if a component is described as being "installed within or connected to" another component, it means that this component may be installed in direct connection or contact with the other component and may be installed in contact with the other component and It may be installed at a certain distance, and in the case where it is installed at a certain distance, there may be a third component or means for fixing or connecting the component to another component. It should be noted that the description of the components or means of 3 may be omitted.

On the other hand, when a component is described as being “directly connected” or “directly connected” to another component, it should be understood that no third component or means is present.

Likewise, other expressions that describe the relationship between components, such as "between" and "immediately between", or "neighboring" and "directly neighboring", have the same meaning. It should be interpreted as

In addition, if terms such as "one side", "other side", "one side", "the other side", "first", "second", etc. are used in this specification, it refers to one component. It is used to clearly distinguish it from other components, and it should be noted that the meaning of the component is not limited by this term.

In addition, if terms related to position such as "top", "bottom", "left", "right", etc. are used in this specification, it should be understood that they indicate the relative position of the corresponding component in the corresponding drawing. Unless the absolute location is specified, these location-related terms should not be understood as referring to the absolute location.

In addition, in this specification, when specifying the reference numeral for each component in each drawing, the same component has the same reference number even if the component is shown in different drawings, that is, the same reference is made throughout the specification. The symbols indicate the same component.

In the drawings attached to this specification, the size, position, connection relationship, etc. of each component constituting the present invention is exaggerated, reduced, or omitted in order to convey the idea of the present invention sufficiently clearly or for convenience of explanation. It may be described, and therefore its proportions or scale may not be exact.

In addition, hereinafter, in describing the present invention, detailed descriptions of configurations that are judged to unnecessarily obscure the gist of the present invention, for example, known technologies including prior art, may be omitted.

Hereinafter, embodiments of the present invention will be described in detail with reference to the related drawings.

Figure 1 is a block diagram showing the overall configuration of a vision system for building process data according to the present invention.

Referring to FIG. 1, the vision system 1000 for constructing process data according to the first embodiment of the present invention includes a 7-segment display unit 100, an input unit 200, a server 300, and a monitoring unit. Includes 400.

The 7-segment display unit 100 displays data in a 7-segment format regarding production management status or process management status.

Here, the 7-segment display unit 100 is implemented by a program that expresses numerical values in 7-segment form to create an environment similar to an actual process site.

The input unit 200 serves to receive data displayed on the 7-segment display unit 100.

That is, the input unit 200 is implemented by vision processing application software that can be applied to various process situations created using a 7-segment program.

The server 300 has a DB that receives data from the input unit 100 in real time and stores and manages it.

This server 300 includes a DB that receives data on the process line recognized through the vision processing application software of the input unit 200 in real time, and serves to communicate with the program of the monitoring unit 400, which will be described later. Perform.

The core of a production management system or process management system is production management through data analysis, and for this, a DB is needed to store recognized values.

Such a DB can be built with MYSQL or Maria DB, for example.

The monitoring unit 400 serves to monitor or analyze data stored in the server 300.

Here, the monitoring unit 400 is implemented by a PC program running on a PC or an app running on a mobile communication terminal, and can monitor and analyze data stored in the DB in real time through such a PC program or app.

In particular, the PC program may be a UI program in a Windows environment for efficient data monitoring and analysis.

Next, the vision system 1000 for constructing process data according to the second embodiment of the present invention includes a 7-segment display unit 100, an input unit 200, a server 300, and a monitoring unit 400. Includes.

The 7-segment display unit 100 displays data in a 7-segment format regarding production management status or process management status.

Here, the 7-segment display unit 100 is implemented by a program that expresses numerical values in 7-segment form to create an environment similar to an actual process site.

The input unit 200 serves to receive data displayed on the 7-segment display unit 100.

That is, the input unit 200 is implemented by vision processing application software that can be applied to various process situations created using a 7-segment program.

The server 300 has a DB that receives data from the input unit 100 in real time and stores and manages it.

This server 300 includes a DB that receives data on the process line recognized through the vision processing application software of the input unit 200 in real time, and serves to communicate with the program of the monitoring unit 400, which will be described later. Perform.

The core of a production management system or process management system is production management through data analysis, and for this, a DB is needed to store recognized values.

Such a DB can be built with MYSQL or Maria DB, for example.

The monitoring unit 400 serves to monitor or analyze data stored in the server 300.

Here, the monitoring unit 400 is implemented by a PC program running on a PC or an app running on a mobile communication terminal, and can monitor and analyze data stored in the DB in real time through such a PC program or app.

In particular, the PC program may be a UI program in a Windows environment for efficient data monitoring and analysis.

Meanwhile, in the vision system 1000 for building process data according to the second embodiment of the present invention, the input unit 200 includes a photographing unit 210 and a learning module 220.

The photographing unit 210 functions to photograph data formed in a 7-segment form.

This photographing unit 210 may use, for example, an IP camera.

The learning module 220 performs learning to read data captured by the photographing unit 210.

Next, the vision system 1000 for constructing process data according to the third embodiment of the present invention includes a 7-segment display unit 100, an input unit 200, a server 300, and a monitoring unit 400. Includes.

The 7-segment display unit 100 displays data in a 7-segment format regarding production management status or process management status.

Here, the 7-segment display unit 100 is implemented by a program that expresses numerical values in 7-segment form to create an environment similar to an actual process site.

The input unit 200 serves to receive data displayed on the 7-segment display unit 100.

That is, the input unit 200 is implemented by vision processing application software that can be applied to various process situations created using a 7-segment program.

The server 300 has a DB that receives data from the input unit 100 in real time and stores and manages it.

This server 300 includes a DB that receives data on the process line recognized through the vision processing application software of the input unit 200 in real time, and serves to communicate with the program of the monitoring unit 400, which will be described later. Perform.

The core of a production management system or process management system is production management through data analysis, and for this, a DB is needed to store recognized values.

Such a DB can be built with MYSQL or Maria DB, for example.

The monitoring unit 400 serves to monitor or analyze data stored in the server 300.

Here, the monitoring unit 400 is implemented by a PC program running on a PC or an app running on a mobile communication terminal, and can monitor and analyze data stored in the DB in real time through such a PC program or app.

In particular, the PC program may be a UI program in a Windows environment for efficient data monitoring and analysis.

Meanwhile, in the vision system 1000 for building process data according to the third embodiment of the present invention, the server 300 monitors the monitoring unit 400 when the data received from the input unit 200 is outside a predetermined normal range. Provides an alarm.

That is, if the data received from the input unit 200 deviates from the standard value preset by the data manager, an alarm is provided to notify the manager for quick identification and response.

Next, the vision system 1000 for constructing process data according to the fourth embodiment of the present invention includes a 7-segment display unit 100, an input unit 200, a server 300, and a monitoring unit 400. Includes.

The 7-segment display unit 100 displays data in a 7-segment format regarding production management status or process management status.

Here, the 7-segment display unit 100 is implemented by a program that expresses numerical values in 7-segment form to create an environment similar to an actual process site.

The input unit 200 serves to receive data displayed on the 7-segment display unit 100.

That is, the input unit 200 is implemented by vision processing application software that can be applied to various process situations created using a 7-segment program.

The server 300 has a DB that receives data from the input unit 100 in real time and stores and manages it.

This server 300 includes a DB that receives data on the process line recognized through the vision processing application software of the input unit 200 in real time, and serves to communicate with the program of the monitoring unit 400, which will be described later. Perform.

The core of a production management system or process management system is production management through data analysis, and for this, a DB is needed to store recognized values.

Such a DB can be built with MYSQL or Maria DB, for example.

The monitoring unit 400 serves to monitor or analyze data stored in the server 300.

Here, the monitoring unit 400 is implemented by a PC program running on a PC or an app running on a mobile communication terminal, and can monitor and analyze data stored in the DB in real time through such a PC program or app.

In particular, the PC program may be a UI program in a Windows environment for efficient data monitoring and analysis.

Meanwhile, in the vision system 1000 for building process data according to the fourth embodiment of the present invention, learning data for learning is generated using the 7-segment display unit 100 and the imaging unit 210, and the learning module (220) performs learning using the generated learning data.

This learning module 220 generates learning data for learning using the 7-segment display unit 100 and the photographing unit 210, and the learning module 220 is a module learned using the generated learning data. This is installed.

Next, the vision system 1000 for constructing process data according to the fifth embodiment of the present invention includes a 7-segment display unit 100, an input unit 200, a server 300, and a monitoring unit 400. Includes.

The 7-segment display unit 100 displays data in a 7-segment format regarding production management status or process management status.

Here, the 7-segment display unit 100 is implemented by a program that expresses numerical values in 7-segment form to create an environment similar to an actual process site.

The input unit 200 serves to receive data displayed on the 7-segment display unit 100.

That is, the input unit 200 is implemented by vision processing application software that can be applied to various process situations created using a 7-segment program.

The server 300 has a DB that receives data from the input unit 100 in real time and stores and manages it.

This server 300 includes a DB that receives data on the process line recognized through the vision processing application software of the input unit 200 in real time, and serves to communicate with the program of the monitoring unit 400, which will be described later. Perform.

The core of a production management system or process management system is production management through data analysis, and for this, a DB is needed to store recognized values.

Such a DB can be built with MYSQL or Maria DB, for example.

The monitoring unit 400 serves to monitor or analyze data stored in the server 300.

Here, the monitoring unit 400 is implemented by a PC program running on a PC or an app running on a mobile communication terminal, and can monitor and analyze data stored in the DB in real time through such a PC program or app.

In particular, the PC program may be a UI program in a Windows environment for efficient data monitoring and analysis.

Meanwhile, in the vision system 1000 for building process data according to the fifth embodiment of the present invention, the monitoring unit 400 can search data stored in the DB and visualize the searched data.

- Example -

Figure 2 is a diagram showing an embedded module of a vision system for building process data according to the present invention.

1) Embedded module

Referring to Figure 2, a 7-segment display program is created and various 7-segment numeric data are produced.

Using a deep learning-based image processing algorithm, learning is performed after labeling into 20 classes.

Here, the 20 classes are 0 to 9 and the numbers 0. to 9. including decimal points.

By applying the learned model to the embedded module environment, the 7-segment display UI program is filmed directly with an IP camera connected to the embedded module, and the 7-segment numbers are recognized as data values.

2) Server

For after-sales support and versatility, it runs on the CentOS8 operating system and uses Maria DB.

Data recognized and sent by the learning module 220 is stored in the DB, and can be utilized by C#-based UI programs and mobile phone applications.

Since direct communication with the DB is not possible in the user application, a PHP file for this is uploaded to the server 300.

When an error occurs in the data value received from the server 300, the DB is periodically checked to notify the administrator, and then alarms such as error messages and notifications are provided to the client UI.

3) Monitoring department

It is implemented as a program using C# Windows Form to check data stored in the server 300 more simply and quickly.

You can monitor each device registered on the server 300 and check logs stored in the DB.

To facilitate data analysis, a function that displays numerical changes in charts is implemented.

Administrators can manage devices and users through the program without directly accessing the DB.

Even if the manager is not at the process site, it can help with efficient process data monitoring.

There may be multiple administrators, and the devices that can be viewed are different for each administrator authority level.

If incorrect data comes out of the device, an alarm is generated so the administrator can respond immediately.

The user application runs on Android devices.

It consists of three tabs, allowing users to view data in their desired format.

This allows data monitoring even if the manager is not at the process site.

Additionally, you can track what problems occurred in the process through the time when incorrect data was generated.

Figure 3 is a diagram showing the state in which primary learning has occurred in the learning module of the vision system for building process data according to the present invention.

1) Embedded module

- problem -

The learning module 220 and the IP camera of the recording unit 210 must be linked to perform streaming.

If the frames per second (FPS) is high, frame lag occurs.

When the learning module 220 is executed, streaming is forcibly terminated due to high memory usage.

It must be minimally affected by the on-site lighting environment or external environment.

The system must be applicable to a variety of 7-segment equipment.

If the detected number is within the same 7-segment area, it must be treated as one object.

That is, the learning module 220 algorithm detects numbers individually.

- Solutions -

The embedded module performs video URL streaming through RTSP (real-time streaming protocol).

The IP camera of the photographing unit 210 minimizes the delay rate by modifying the environmental configuration (maximum frame, resolution, etc.).

Referring to FIG. 3, this is the result of learning data produced by screen capture in the learning module 220 of the vision system 1000 for constructing process data according to the present invention.

When an actual 7-segment device detects numbers in real time through the IP camera of the photographing unit 210, it can be confirmed that some numbers cannot be detected.

Figure 4 is a diagram showing a state in which secondary learning is performed in the learning module of the vision system for building process data according to the present invention.

Referring to FIG. 4, data captured by the IP camera of the photographing unit 210 was added to the learning data.

We trained about 3,500 numbers 12,000 times based on 83 environments while changing lighting and segment colors.

As a result of learning, it was confirmed that most numbers were recognized at a level of 99 to 100%, but for some numbers, the accuracy decreased to 60 to 90%.

Figure 5 is a diagram showing a state in which 3rd learning has occurred in the learning module of the vision system for building process data according to the present invention.

Referring to Figure 5, the data was processed in gray scale as preprocessing without considering multiple colors.

Here, the method of using a model that learned gray-scale processed data has higher accuracy than a model that learned a separate color.

In the third round of learning, all existing learning data was processed in gray scale.

As a result of actually testing the learned model, it was confirmed that numbers were detected with an accuracy of 99 to 100%.

A problem occurred in the embedded module, causing it to shut down due to lack of resources.

Figure 6 is a diagram showing the state in which fourth learning has occurred in the learning module of the vision system for building process data according to the present invention.

Referring to FIG. 6, a lightweight model was created using the learning module 220.

Through augmentation, learning was conducted by rotating the learning data from 0 to 30 degrees left and right and increasing the data.

Using the built-in function of the learning module (220), learning was conducted to distinguish between left and right, and learning was conducted to distinguish between 2 and 5.

As a result of applying the lightweight model to the embedded module, it was confirmed that it operates smoothly without shutdown problems.

When conducting a test using the IP camera of the recording unit 210, numbers that were not recognized were found.

Figure 7 is a diagram showing the state in which the 5th learning is performed in the learning module of the vision system for building process data according to the present invention.

Referring to Figure 7, data produced through the IP camera of the recording department was additionally studied.

As a result of the actual test, numbers were detected with an accuracy of 99% to 100%, so it was decided as the final learning model.

2) Server

- problem -

A separate server 300 and DB manager may not exist in a factory using an existing production process.

Access must be easy from all camera (embedded) parts, PC UI program parts, and mobile application parts.

Since the client must always be connected to the server for the notification function, a way to reduce the load caused by this is needed.

- Solutions -

Problems occurring in the server 300 and DB can be resolved relatively easily.

In other words, Cent OS and Maria DB are used, and the operating system can be switched to RedHat Linux, a paid OS that provides technical support in case of emergency. Maria DB shares the system with MYSQL, the most widely used in Korea, so administrators can relatively easily access related information. You can find .

It is easy to access in both the Linux environment of the learning module 220, the C# form of the client UI, and Android (Java).

You can find a method to establish a connection to MYSQL in various environments and pass it on and apply it to each part.

Continuing to search the DB to use the notification function may place a load on both the server and the client, so create a dedicated table for sending notifications, and set the server (300) to check the table and send if an error value occurs. did.

Data entering the table is automatically copied through the DB trigger function.

3) Monitoring Department Program

- problem -

Security issues may arise if a user has access to all registered devices.

When the number of data increases too much, it is difficult to find values in a specific time period or strange numbers.

For security and professional reasons, it is not recommended for general users to directly access the DB to register devices.

- Solutions -

It must be possible to restrict user access to each device.

In response to this, levels were created for user permissions so that users with permissions lower than the device level could not access information on the device.

It must be possible to visually check changes in data values and the numbers needed for analysis.

In response to this, a chart tab was implemented to check when an outlier occurred, the corresponding value, and changes in the numerical value.

Users must be able to add/edit information about the device without directly accessing the DB.

In response to this, the client program was modified to perform device and user management functions.

Figure 8 is a diagram showing a state in which learning has been completed in the learning module of the vision system for building process data according to the present invention.

Referring to FIG. 8, in the vision system 1000 for building process data according to the present invention, a 7-segment number can be detected using a model that has completed training in the learning module 220.

Figure 9 is a diagram showing data detected by the server of the vision system for building process data according to the present invention.

Referring to FIG. 9, in the vision system 1000 for constructing process data according to the present invention, data detected in the DB of the server 300 can be confirmed.

Figure 10 is a diagram showing data sets for each device displayed on the monitoring unit of the vision system for building process data according to the present invention.

Referring to FIG. 10, a tab showing one set of latest data for each device can be seen in the monitoring unit 400 of the vision system 1000 for building process data according to the present invention.

Figure 11 is a diagram showing data for a specified period viewed from the monitoring unit of the vision system for building process data according to the present invention.

Referring to FIG. 11, it can be seen that the monitoring unit 400 of the vision system 1000 for building process data according to the present invention can view all data from a desired device during a period specified by the user.

Figure 12 is a diagram showing login in the monitoring unit of the vision system for building process data according to the present invention.

Referring to FIG. 12, it can be seen that the monitoring unit 400 of the vision system 1000 for building process data according to the present invention can visualize and search all data from a desired device during a period specified by the user.

Figure 13 is a diagram showing an alarm displayed when a data error occurs in the monitoring unit of the vision system for building process data according to the present invention.

Referring to FIG. 13, in the monitoring unit 400 of the vision system 1000 for constructing process data according to the present invention, an alarm received when data outside the normal range occurs can be confirmed.

In this way, according to the present invention, it is possible to perform the function of a production management system by supplementing the existing process line at a lower cost.

Above, various preferred embodiments of the present invention have been described by giving some examples, but the description of the various embodiments described in the "Detailed Contents for Carrying out the Invention" section is merely illustrative and the present invention Those skilled in the art will understand from the above description that the present invention can be implemented with various modifications or equivalent implementations of the present invention.

In addition, since the present invention can be implemented in various other forms, the present invention is not limited by the above description, and the above description is intended to make the disclosure of the present invention complete and is commonly used in the technical field to which the present invention pertains. It is provided only to fully inform those with knowledge of the scope of the present invention, and it should be noted that the present invention is only defined by each claim in the claims.

100: 7-segment display
200: input unit
210: IP camera
220: Learning module
300: Server
400: monitoring unit
1000: Vision system for building process data

Claims (5)

A 7-segment display unit that displays data in 7-segment form regarding production management status or process management status;
an input unit that receives data displayed on the 7-segment display unit;
A server having a DB that receives data from the input unit in real time and stores and manages the data; and
It includes a monitoring unit that monitors or analyzes data stored in the server,
The server is,
If the data received from the input unit is outside a predetermined normal range, an alarm is provided to the monitoring unit,
The input unit,
a photographing unit that photographs data formed in the 7-segment form; and
It includes a learning module that performs learning to read data captured by the photographing unit,
Generating learning data for learning using the 7-segment display unit and the capturing unit,
The learning module performs learning using the generated learning data,
When performing the above learning, video URL streaming is performed through RTSP (real-time streaming protocol),
The photographing unit minimizes the frame delay rate by modifying the maximum frame and resolution,
Learning is conducted based on multiple environments by changing lighting and segment colors.
During preprocessing, the data is processed into gray scale,
A vision system for building process data, characterized in that the learning data is rotated from 0 to 30 degrees left and right through augmentation and the data is increased to learn. delete delete delete A 7-segment display unit that displays data in 7-segment form regarding production management status or process management status;
an input unit that receives data displayed on the 7-segment display unit;
A server having a DB that receives data from the input unit in real time and stores and manages the data; and
It includes a monitoring unit that monitors or analyzes data stored in the server,
The server is,
If the data received from the input unit is outside a predetermined normal range, an alarm is provided to the monitoring unit,
The monitoring unit,
You can search the data stored in the DB and visualize the searched data,
The input unit,
a photographing unit that photographs data formed in the 7-segment form; and
It includes a learning module that performs learning to read data captured by the photographing unit,
Generating learning data for learning using the 7-segment display unit and the capturing unit,
The learning module performs learning using the generated learning data,
When performing the above learning, video URL streaming is performed through RTSP (real-time streaming protocol),
The photographing unit minimizes the frame delay rate by modifying the maximum frame and resolution,
Learning is conducted based on multiple environments by changing lighting and segment colors.
During preprocessing, the data is processed into gray scale,
Characterized by rotating the learning data from 0 to 30 degrees left and right through augmentation and increasing the data to proceed with learning.
Vision system for building process data.