KR102274856B1 - System and method for analyzing failure of linkage type of MES of automated system - Google Patents

Abstract

A failure analysis system and method capable of analyzing the cause of failure of an automation facility in connection with the MES (Manufacturing Execution System Shop Floor) of the automation facility are provided. MES-linked failure analysis method according to an embodiment of the present invention comprises the steps of: individually collecting, by a data collection unit, data input or output from each control system that individually controls each facility; Generating, by the data learning unit, each of the collected data by machine learning (machine learning) each model data (model data); Predicting, by the data prediction unit, the next data individually based on each model data; Determining, by the facility abnormality determination unit, the abnormality of a plurality of contact points constituting each facility based on each model data and each prediction data, in units of cycles composed of a plurality of contact points; and inferring, by the cause diagnosis unit, the cause of the failure of the abnormal cycle by using the characteristics of the model data used to determine whether the specific cycle is abnormal. As a result, the failure analysis means of automated equipment can automatically perform failure cause analysis of production equipment and link the results with the existing MES, thereby reducing equipment maintenance time and equipment downtime, and troubleshooting time and cost. can save In addition, it is possible to determine whether the plurality of contact points constituting each facility is abnormal in units of cycles composed of the plurality of contact points, thereby improving the efficiency of equipment abnormality determination.

Description

MES interlocking failure analysis system and method of automated equipment {System and method for analyzing failure of linkage type of MES of automated system}

The present invention relates to a failure analysis system and method of an automated facility, and more particularly, in connection with the MES (Manufacturing Execution System Shop Floor) of an automated facility, to a failure analysis system and method that can analyze the cause of failure of an automated facility it's about

In order to automatically control process equipment, in the prior art, as shown in FIG. 1, when a failure occurs in process automation equipment using PLC, a highly skilled technician who can maintain the equipment goes directly to the on-site automation equipment and uses a laptop computer. And by using various testers, the PLC program, which is the controller of the automation facility, was monitored to find the part where the failure occurred and the cause was analyzed.

However, when the factory where the automation equipment is installed is located in a remote place such as overseas, it takes a lot of time and money because a highly skilled technician has to move to repair the automation equipment.

In addition, when highly skilled technicians are arranged in a plurality of factories, there is a problem in that a lot of time and money are required for training the technicians.

In addition, in the event of a facility failure, there is an inconvenience of having to go to the front of the broken facility and check the monitor to check the failure analysis.

Therefore, it is required to find a way to perform failure cause analysis of production equipment in the failure analysis means of automated equipment and link the results with the existing MES.

delete

Korean Patent Application Laid-Open No. 10-2019-0085291 (Title of the invention: Failure analysis apparatus and method for automated equipment)

The present invention has been devised to solve the above problems, and an object of the present invention is to automatically perform a failure cause analysis of a production facility in a failure analysis means of an automated facility, and to link the results with the existing MES. An object of the present invention is to provide an MES-linked failure analysis system and method of an automated facility.

Another object of the present invention is to provide an MES-linked failure analysis system and method of an automated facility that can determine whether or not a plurality of contact points constituting each facility are abnormal in a cycle unit composed of a plurality of contact points.

In accordance with an embodiment of the present invention for achieving the above object, the MES-linked failure analysis method includes: individually collecting, by a data collection unit, data input or output from each control system that individually controls each facility ; Generating, by the data learning unit, each of the collected data by machine learning (machine learning) each model data (model data); Predicting, by the data prediction unit, the next data individually based on each model data; Determining, by the equipment abnormality determination unit, the abnormality of the plurality of contact points constituting each facility on the basis of each model data and each prediction data, in units of cycles composed of the plurality of contact points; and inferring, by the cause diagnosis unit, the cause of the failure of the cycle in the abnormal state by using the characteristics of the model data used to determine whether the specific cycle is abnormal.

In addition, the collecting step may collect input or output data including tag information for identification of each control system.

In addition, each control system may automatically register the tag information in the operation tag list of the data collection unit when the operation starts.

In addition, in the collecting step, the data collection unit checks the operation status of the control systems automatically registered in the operation tag list according to a preset period, and separates the tag information of the control systems whose operation is currently stopped from the operation tag list, In the step of moving to the interruption tag list, transferring the moved interruption tag list to the equipment abnormality determination unit, and determining, the equipment abnormality determination unit first determines whether the cycles controlled by the control system included in the interruption tag list are abnormal can do.

In addition, the characteristic of the model data may be at least one of a contact order, a contact appearance frequency, a predicted data hit rate, and a degree of correlation between the contact points.

In addition, in the determining step, it is possible to determine whether the cycles are abnormal based on whether the prediction data is present or whether the prediction data is hit.

And in the determining step, if a characteristic that proceeds in a specific contact order with respect to a plurality of contact points constituting one cycle is included in the model data, if there is no predictive data, it is registered in the unpredictable data list, and the specific contact point If a contact different from the order is performed and the prediction data does not hit, it can be registered in the prediction failure data list.

In addition, the predicting step determines the priority of data registered in the unpredictable data list and the prediction failure data list, but by rearranging the data registered in the unpredictable data list and the prediction failure data list in consideration of the characteristics of the model data. , high priority can be given to data with high probability of failure.

And, in the MES-linked failure analysis method according to an embodiment of the present invention, when the monitoring unit determines that a specific cycle is in a normal state, depending on whether a specific cycle is abnormal, operation information of a control system for controlling a cycle in a normal state and outputting failure cause information of the cycle in the abnormal state when it is determined that the specific cycle is in an abnormal state; may further include.

In addition, in the step of outputting, at the request of the administrator, the operation time and the number of operations operated for a preset period may be output for each control system.

And the outputting step may individually output the real-time operation state of each control system upon a request of an administrator.

In addition, in the outputting step, when it is determined that a specific cycle is in an abnormal state, information on the cause of failure of the cycle in the abnormal state and whether another cycle of the control system controlling the cycle in the abnormal state is abnormal may be output together.

In the outputting step, upon a request of an administrator, history information for a cycle determined as an abnormal state among a plurality of cycles controlled by each control system may be output.

On the other hand, it goes without saying that the technical idea of the present invention can also be applied to a computer-readable recording medium containing a computer program for performing the functions of the apparatus and method according to the present embodiment. In addition, the technical ideas according to various embodiments of the present invention may be implemented in the form of computer-readable codes recorded on a computer-readable recording medium. The computer-readable recording medium may be any data storage device readable by the computer and capable of storing data. For example, the computer-readable recording medium may be a ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical disk, hard disk drive, or the like. In addition, the computer-readable code or program stored in the computer-readable recording medium may be transmitted through a network connected between computers.

In addition, according to another embodiment of the present invention, the MES-linked failure analysis system includes: a data collection unit for individually collecting data input or output from each control system that individually controls each facility; a data learning unit for generating each model data by machine learning each collected data; a data prediction unit that individually predicts the next data based on each model data; a facility abnormality determination unit that determines whether a plurality of contact points constituting each facility are abnormal on the basis of each model data and each prediction data in units of a cycle composed of a plurality of contact points; and a cause diagnosis unit for inferring the cause of the failure of the cycle in the abnormal state by using the characteristics of the model data used to determine whether the specific cycle is abnormal.

As described above, according to the embodiments of the present invention, it is possible to automatically perform the failure cause analysis of the production equipment in the failure analysis means of the automated equipment and link the results with the existing MES, so that the equipment maintenance time and equipment cost are reduced. It can shorten the time and save the trouble-shooting time and cost.

According to embodiments of the present invention, it is possible to determine whether a plurality of contact points constituting each facility is abnormal in units of a cycle composed of a plurality of contact points, thereby improving the efficiency of equipment abnormality determination.

1 is a view provided for the description of a countermeasure method in the event of a failure of an existing automated facility;
2 to 3 are diagrams provided for the description of the MES-linked failure analysis system and method according to an embodiment of the present invention;
4 is a view provided for explaining the configuration of an MES-linked failure analysis system according to an embodiment of the present invention;
5 is a flowchart provided for the description of an MES-linked failure analysis method according to an embodiment of the present invention, and
6 to 7 are diagrams illustrating a state in which a monitoring result of a facility is output using the MES-linked failure analysis method according to an embodiment of the present invention.

Hereinafter, the present invention will be described in more detail with reference to the drawings.

2 to 3 are diagrams provided for the description of the MES-linked failure analysis system 100 and method according to an embodiment of the present invention, and FIG. 4 is an MES-linked failure analysis system according to an embodiment of the present invention ( 100) is a diagram provided for the description of the configuration.

The MES-linked failure analysis system 100 according to an embodiment of the present invention can automatically perform failure cause analysis of production facilities, and link the results with the existing MES 10, and configure each facility. Whether or not the plurality of contact points is abnormal may be determined in units of cycles composed of the plurality of contact points.

To this end, the MES-linked failure analysis system 100 includes a control system 110 , a data collection unit 120 , a data learning unit 130 , a data prediction unit 140 , a facility abnormality determination unit 150 , and a cause. It may include a diagnosis unit 160 , a monitoring unit 170 , and a storage unit 180 .

The control system 110 may control each facility individually, collect data for each facility, and transmit it to the data collection unit 120 .

In addition, the control system 110 adds unique tag information to the data to be transmitted to the data collection unit 120 , so that the data collection unit 120 identifies the data received from which control system 110 . can make it possible

To this end, the control system 110 includes a sensor 111 that collects data on facilities connected for control, a tag unit 112 that stores unique tag information, and a processor 113 that adds tag information to the collected data. ), and a communication unit 114 that transmits the data to which the tag information is added to the data collection unit 120 .

The data collection unit 120 may individually collect data input or output from each control system 110 that individually controls each facility.

At this time, each control system 110 adds tag information to the data indicating that the operation is started, and transmits it to the data collection unit 120, so that the tag information of the corresponding control system 110 is transferred to the data collection unit ( 120) can be automatically registered in the action tag list.

In addition, the data collection unit 120 checks the operation status of the control systems 110 automatically registered in the operation tag list according to a preset period, and collects tag information of the control systems 110 that are currently stopped in operation from the operation tag list. It is possible to separate from and move to the stop tag list, and transfer the moved stop tag list to the facility abnormality determination unit 150 .

The data learning unit 130 may generate each model data by machine learning each collected data.

The data prediction unit 140 may individually predict the next data based on each model data.

The control system 110 is configured to control a plurality of contact points in order to automate the facility. Specifically, for example, when a task performed by a specific facility is composed of four individual contacts of A, B, C, and D, , A, B, C, D can be controlled so that the operation is performed in the order of ABCD.

In this case, the data prediction unit 140 may predict the next data based on the model data generated by machine learning by the data learning unit 130 .

That is, the model data includes the characteristic that the contact proceeds in the order of ABCD, and the data prediction unit 140 individually predicts the next data while monitoring each control system 110 in real time based on each model data. can proceed with

For example, when the data prediction unit 140 confirms that the A contact is performed, it predicts that the next B contact will proceed, and predicts input/output data corresponding to the B contact.

In this way, the data prediction unit 140 may generate prediction data by predicting the contact point to be performed next based on the model data generated by the data learning unit 130 .

Here, each facility may include a plurality of automated process cycles, and each cycle may be configured to include a plurality of contact points.

The facility abnormality determination unit 150 may determine whether each facility is abnormal based on each model data and each prediction data.

For example, the facility abnormality determination unit 150 may determine whether the cycles are abnormal based on whether the prediction data exists or whether the prediction data is hit.

In addition, the equipment abnormality determination unit 150, based on each model data and each predicted data, by determining whether or not the plurality of contact points constituting each facility is abnormal in units of a cycle composed of a plurality of contact points, the facility It is possible to improve the efficiency of abnormal judgment.

In this case, when the number of unit contacts is composed of thousands, it is more important to determine whether the abnormality is in a unit of cycle including a plurality of contacts rather than determining whether the abnormality is in the unit of contact in the equipment abnormality determination unit. This is because the throughput will be significantly reduced.

And the equipment abnormality determination unit 150, if the model data includes a characteristic that proceeds in a specific contact order with respect to a plurality of contact points constituting one cycle, if there is no predictive data, it is registered in the unpredictable data list and , when a contact different from the specific contact order is performed and the prediction data does not hit, it can be registered in the prediction failure data list.

In this case, the cause diagnosis unit 160 determines the priority of data registered in the unpredictable data list and the predictive failure data list, and uses the data registered in the unpredictable data list and the predictive failure data list to characterize the model data. By reordering in consideration, it is possible to give high priority to data with a high probability of causing a failure.

In addition, the equipment abnormality determination unit 150, when the interruption tag list is received, by preferentially determining whether the cycles controlled by the control system 110 included in the received interruption tag list are abnormal, the efficiency of equipment abnormality determination can improve

If the cause diagnosis unit 160 determines that a specific cycle is in an abnormal state, the cause diagnosis unit 160 may infer the cause of the failure of the abnormal cycle by using the characteristics of the model data used to determine whether there is an abnormality. have.

The characteristic of the model data may be at least one of a contact order, a contact appearance frequency, a predicted data hit rate, and a degree of association between the contact points.

That is, in the model data, reference information about the contact order in which the contact points proceed in the same order as ABCD, the frequency of appearance of each contact point such as A, B, C, B, and data predicted by the data prediction unit 140 (or contact points) ) may be included in the actual hit rate, the degree of relevance between the A contact and the B contact or the C contact.

That is, the cause diagnosis unit 160 determines that the abnormal state is abnormal and rearranges the listed abnormal data in consideration of the characteristics of the model data, and gives high priority to data having a high probability of causing a failure.

Specifically, the cause diagnosis unit 160 determines the priority of data registered in the unpredictable data list and the predictive failure data list, but uses the data registered in the unpredictable data list and the predictive failure data list to characterize the model data. By reordering in consideration, it is possible to give high priority to data with a high probability of causing a failure.

The monitoring unit 170 outputs operation information of the control system 110 for controlling a cycle in a normal state when determining that a specific cycle is in a normal state, depending on whether a specific cycle is abnormal, and determines that the specific cycle is in an abnormal state. In this case, information on the cause of failure of the cycle in an abnormal state can be output.

For example, the monitoring unit 170 may display the faulty part on the three-dimensional image based on the analyzed cause of the failure so that the operator can more intuitively and quickly identify the faulty part, and indicate the faulty part with text.

In addition, the monitoring unit 170 may output, for each control system 110 , the operation time and the number of operations operated for a preset period at the request of the manager.

In addition, the monitoring unit 170 may individually output the real-time operation state of each control system 110 at the request of the manager.

In addition, when the monitoring unit 170 determines that a specific cycle is in an abnormal state, information on the cause of failure of the abnormal cycle and the abnormality of another cycle of the control system 110 for controlling the abnormal cycle can be output together. have.

In addition, the monitoring unit 170 may output history information on a cycle determined as an abnormal state among a plurality of cycles controlled by each control system 110 at the request of the manager.

The storage unit 180 is a storage medium capable of storing programs and data necessary for the MES-linked failure analysis system 100 to operate.

For example, the storage unit 180 may store data for machine learning, model data and prediction data, and data for each control system 110 .

5 is a flowchart provided to explain the MES-linked failure analysis method according to an embodiment of the present invention, and FIGS. 6 to 7 are the MES-linked failure analysis method according to an embodiment of the present invention, using the MES-linked failure analysis method, It is a diagram exemplifying a state in which the monitoring result is output.

5 to 7 , in the MES-linked failure analysis method according to the present embodiment, the data collection unit 120 is input or output from each control system 110 that individually controls each facility. When data is individually collected ( S510 ), the data learning unit 130 may generate each model data by machine learning each collected data ( S520 ).

And when the data prediction unit 140 individually predicts the next data based on each model data, and generates each prediction data (S530), the facility abnormality determination unit 150, each model data and each Whether or not the plurality of contact points constituting each facility is abnormal based on the predicted data of may be determined in units of cycles composed of the plurality of contact points ( S540 ).

In addition, when it is determined that a specific cycle is in an abnormal state (S550-N), the cause diagnosis unit 160 may infer the cause of the failure of the abnormal cycle by using the characteristics of the model data used to determine whether there is an abnormality. (S570).

That is, when it is determined that a specific cycle is in a normal state (S550-Y) according to whether a specific cycle is abnormal, the monitoring unit 170 outputs operation information of the control system 110 for controlling the cycle in a normal state ( S560), when it is determined that the specific cycle is in an abnormal state (S550-N), the monitoring unit 170 may output information on the cause of failure of the cycle in the abnormal state (S580).

At this time, the monitoring unit 170 may output whether a specific facility (eg, a fusion facility of a vehicle door trim) is abnormal for each automated process cycle, as illustrated in FIG. 6 , and as illustrated in FIG. 7 , the specific facility It is possible to output the history of past failures (ex. fusion equipment for vehicle door trims).

Through this, in order to save failure resolution time and cost, the failure analysis means of the automated equipment can automatically perform the failure cause analysis of the production equipment, and the results can be linked with the existing MES. It is possible to determine whether or not the contact points are abnormal in units of a cycle composed of a plurality of contact points, thereby improving the efficiency of equipment abnormality determination.

On the other hand, it goes without saying that the technical idea of the present invention can also be applied to a computer-readable recording medium containing a computer program for performing the functions of the apparatus and method according to the present embodiment. In addition, the technical ideas according to various embodiments of the present invention may be implemented in the form of computer-readable codes recorded on a computer-readable recording medium. The computer-readable recording medium may be any data storage device readable by the computer and capable of storing data. For example, the computer-readable recording medium may be a ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical disk, hard disk drive, or the like. In addition, the computer-readable code or program stored in the computer-readable recording medium may be transmitted through a network connected between computers.

In addition, although preferred embodiments of the present invention have been illustrated and described above, the present invention is not limited to the specific embodiments described above, and the technical field to which the present invention belongs without departing from the gist of the present invention as claimed in the claims Various modifications are possible by those of ordinary skill in the art, and these modifications should not be individually understood from the technical spirit or prospect of the present invention.

10: Existing MES system
100: MES-linked failure analysis system
110: control system
111: sensor
112: tag part
113: processor
114: communication department
120: data collection unit
130: data learning unit
140: data prediction unit
150: equipment abnormality determination unit
160: cause diagnosis unit
170: monitoring unit
180: storage

Claims (14)

Collecting, by the data collection unit, data input or output from each control system individually controlling each facility individually;
Generating, by the data learning unit, each of the collected data by machine learning (machine learning) each model data (model data);
Predicting, by the data prediction unit, the next data individually based on each model data;
Determining, by the facility abnormality determination unit, the abnormality of a plurality of contact points constituting each facility based on each model data and each prediction data, in units of cycles composed of a plurality of contact points; and
When determining that a specific cycle is in an abnormal state, the cause diagnosis unit infers the cause of the failure of the abnormal cycle by using the characteristics of the model data used to determine whether there is an abnormality;
The collection steps are:
Collects input or output data including tag information for identification of each control system,
Each control system is
At the start of operation, tag information is automatically registered in the operation tag list of the data collection unit,
The collection steps are:
The data collection unit checks the operation status of the control systems automatically registered in the operation tag list according to a preset period, separates the tag information of the control systems that are currently stopped in operation from the operation tag list, and moves them to the stop tag list, Delivers the moved stop tag list to the facility abnormality determination unit,
The judging step is
The facility abnormality determination unit first determines whether the cycles controlled by the control system included in the stop tag list are abnormal,
The characteristics of the model data are:
It is at least one of the contact order, contact appearance frequency, predicted data hit rate, and correlation between contacts,
The MES-linked failure analysis method is,
When the monitoring unit determines that the specific cycle is in a normal state, depending on whether the specific cycle is abnormal, outputs operation information of the control system for controlling the normal cycle, and when determining that the specific cycle is abnormal, the cycle in the abnormal state Outputting the failure cause information of; further comprising,
The output step is
At the request of the manager, the operation time and number of operations operated for a preset period are output for each control system or the real-time operation status of each control system is individually output,
The output step is
If a specific cycle is judged to be in an abnormal state, information on the cause of the failure of the cycle in the abnormal state and the abnormality of other cycles in the control system that controls the cycle in the abnormal state are output together,
The output step is
MES-linked failure analysis method, characterized in that at the request of an administrator, outputting history information on a cycle determined to be in an abnormal state among a plurality of cycles controlled by each control system.
delete delete delete delete The method according to claim 1,
The judging step is
MES-linked failure analysis method, characterized in that it is determined whether the cycles are abnormal based on the presence of the prediction data or whether the prediction data is hit.
7. The method of claim 6,
The judging step is
If the model data includes a characteristic that proceeds in a specific contact order with respect to a plurality of contact points constituting one cycle, if there is no predictive data, it is registered in the unpredictable data list, and a contact point different from the specific contact order is performed MES-linked failure analysis method, characterized in that when the prediction data does not hit, it is registered in the prediction failure data list.
8. The method of claim 7,
The predicting step is
Determining the priority of data registered in the unpredictable data list and the predictive failure data list, but rearranging the data registered in the unpredictable data list and the predictive failure data list in consideration of the characteristics of the model data, data with a high probability of a cause of failure MES-linked failure analysis method, characterized in that high priority is given to
delete delete delete delete delete a data collection unit for individually collecting data input or output from each control system that individually controls each facility;
A data learning unit for generating each model data (model data) by machine learning (machine learning) each of the collected data;
a data prediction unit that individually predicts the next data based on each model data;
a facility abnormality determination unit that determines whether a plurality of contact points constituting each facility are abnormal on the basis of each model data and each prediction data in units of a cycle composed of a plurality of contact points; and
a cause diagnosis unit for inferring the cause of the failure of the abnormal cycle by using the characteristics of the model data used to determine whether a specific cycle is abnormal;
data collection unit,
Collects input or output data including tag information for identification of each control system,
Each control system is
At the start of operation, tag information is automatically registered in the operation tag list of the data collection unit,
data collection unit,
By checking the operation status of the control systems automatically registered in the operation tag list according to a preset period, the tag information of the control systems that are currently stopped is separated from the operation tag list, moved to the stop tag list, and the moved stop tag The list is delivered to the equipment abnormality judgment unit,
The equipment abnormality judgment unit,
Prioritize whether the cycles controlled by the control system included in the stop tag list are abnormal,
The characteristics of the model data are:
It is at least one of the contact order, contact appearance frequency, predicted data hit rate, and correlation between contacts,
MES-linked failure analysis system,
According to the abnormality of a specific cycle, when a specific cycle is judged to be in a normal state, operation information of the control system that controls the normal cycle is output, and when a specific cycle is judged to be abnormal, the cause of the failure of the abnormal cycle Monitoring unit for outputting information; further comprising,
monitoring department,
At the request of the manager, the operation time and number of operations operated for a preset period are output for each control system or the real-time operation status of each control system is individually output,
monitoring department,
If a specific cycle is judged to be in an abnormal state, information on the cause of the failure of the cycle in the abnormal state and the abnormality of other cycles in the control system that controls the cycle in the abnormal state are output together,
monitoring department,
MES-linked failure analysis system, characterized in that at the request of the manager, outputting history information on the cycle determined to be in an abnormal state among a plurality of cycles controlled by each control system.

Images